{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T11:37:00Z","timestamp":1793878620192,"version":"4.7.0"},"reference-count":210,"publisher":"Association for Computing Machinery (ACM)","issue":"15","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Damo Academy (Hupan Laboratory) through Damo Academy (Hupan Laboratory) Innovative Research Program, Research Grants Council of the Hong Kong Special Administrative Region, China","award":["CUHK 14206625"],"award-info":[{"award-number":["CUHK 14206625"]}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"crossref","award":["JCYJ20220530143002005"],"award-info":[{"award-number":["JCYJ20220530143002005"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shenzhen Ubiquitous Data Enabling Key Lab","award":["ZDSYS20220527171406015"],"award-info":[{"award-number":["ZDSYS20220527171406015"]}]},{"name":"Tsinghua University SIGS Start-up fund","award":["QD2022024C"],"award-info":[{"award-number":["QD2022024C"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,11,30]]},"abstract":"<jats:p>Graph Transformers (GTs) have demonstrated a strong capability in modeling graph structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as over-smoothing and over-squashing. Recent studies have proposed diverse architectures, enhanced explainability, and practical applications for Graph Transformers. In light of these rapid developments, we conduct a comprehensive review of Graph Transformers, covering aspects such as their architectures, theoretical foundations, and applications. In this survey, we first categorize the architecture of Graph Transformers according to their strategies for processing structural information, including graph tokenization, positional encoding, structure-aware attention, and model ensemble. Then, from the theoretical perspective, we examine the expressivity of Graph Transformers in various discussed architectures and contrast them with other advanced graph learning algorithms to discover their connections. For applications, we organize the literature around four graph organization forms, from relational, geometric, dynamic to heterogeneous. A Practical Guidance table then maps architectural components to these graph forms by adoption frequency, so practitioners can narrow down which design families to consider for a given input structure. Lastly, we will discuss the current challenges and prospective directions in Graph Transformers for potential future research.<\/jats:p>","DOI":"10.1145\/3834764","type":"journal-article","created":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T10:10:08Z","timestamp":1784974208000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["A Survey of Graph Transformers: Architectures, Theories and Applications"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7589-9271","authenticated-orcid":false,"given":"Chaohao","family":"Yuan","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, Hong Kong"]},{"name":"Tsinghua University","place":["Hong Kong, Hong Kong"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7189-983X","authenticated-orcid":false,"given":"Kangfei","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, Hong Kong"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2608-8034","authenticated-orcid":false,"given":"Ercan","family":"Kuruoglu","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Shenzhen, China"]},{"name":"ISTI-CNR","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4714-7582","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences Institute of Automation","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0106-8376","authenticated-orcid":false,"given":"Tingyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy","place":["Hangzhou, China"]},{"name":"Hupan Lab","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2566-4159","authenticated-orcid":false,"given":"Wenbing","family":"Huang","sequence":"additional","affiliation":[{"name":"Renmin University of China","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8838-578X","authenticated-orcid":false,"given":"Deli","family":"Zhao","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4673-2587","authenticated-orcid":false,"given":"Hong","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, Hong Kong"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7387-302X","authenticated-orcid":false,"given":"Yu","family":"Rong","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy","place":["Hangzhou, China"]},{"name":"Hupan Lab","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,22]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"2001","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Agarwal Rajat","year":"2022","unstructured":"Rajat Agarwal, Varun Khurana, Karish Grover, Mukesh Mohania, and Vikram Goyal. 2022. Multi-relational graph transformer for automatic short answer grading. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2001\u20132012."},{"key":"e_1_3_1_3_2","unstructured":"Jimmy Lei Ba Jamie Ryan Kiros and Geoffrey E. Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450. Retrieved from https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_1_4_2","first-page":"1","article-title":"The open materials 2024 (OMat24) inorganic materials dataset and models","author":"Barros-Luque Luis","year":"2026","unstructured":"Luis Barros-Luque, Muhammed Shuaibi, Xiang Fu, Brandon M. Wood, Misko Dzamba, Meng Gao, Ammar Rizvi, Matt Uyttendaele, C. Lawrence Zitnick, and Zachary W. Ulissi. 2026. The open materials 2024 (OMat24) inorganic materials dataset and models. Nature Computational Science. Nature Publishing Group US New York, 1\u201311.","journal-title":"Nature Computational Science"},{"key":"e_1_3_1_5_2","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1145\/3637528.3672044","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Behrouz Ali","year":"2024","unstructured":"Ali Behrouz and Farnoosh Hashemi. 2024. Graph mamba: Towards learning on graphs with state space models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 119\u2013130."},{"key":"e_1_3_1_6_2","first-page":"127044","article-title":"Relphormer: Relational graph transformer for knowledge graph representations","volume":"566","author":"Bi Zhen","year":"2023","unstructured":"Zhen Bi, Siyuan Cheng, Jing Chen, Xiaozhuan Liang, Feiyu Xiong, and Ningyu Zhang. 2023. Relphormer: Relational graph transformer for knowledge graph representations. Neurocomputing 566 (2023), 127044.","journal-title":"Neurocomputing"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Black Mitchell","year":"2024","unstructured":"Mitchell Black, Zhengchao Wan, Gal Mishne, Amir Nayyeri, and Yusu Wang. 2024. Comparing graph transformers via positional encodings. In Proceedings of the International Conference on Machine Learning. PMLR."},{"issue":"1","key":"e_1_3_1_8_2","first-page":"i318\u2013i325","article-title":"Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function","volume":"39","author":"Boadu Frimpong","year":"2023","unstructured":"Frimpong Boadu, Hongyuan Cao, and Jianlin Cheng. 2023. Combining protein sequences and structures with transformers and equivariant graph neural networks to predict protein function. Bioinformatics 39, Supplement_1, (2023), i318\u2013i325.","journal-title":"Bioinformatics"},{"key":"e_1_3_1_9_2","article-title":"On the connection between MPNN and graph transformer","author":"Cai Chen","year":"2023","unstructured":"Chen Cai, Truong Son Hy, Rose Yu, and Yusu Wang. 2023. On the connection between MPNN and graph transformer. In Proceedings of the International Conference on Machine Learning.","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"e_1_3_1_10_2","volume-title":"Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI)","author":"Cai Deng","year":"2020","unstructured":"Deng Cai and Wai Lam. 2020. Graph transformer for graph-to-sequence learning. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI)."},{"issue":"2","key":"e_1_3_1_11_2","first-page":"456","article-title":"Graph transformer geometric learning of brain networks using multimodal MR images for brain age estimation","volume":"42","author":"Cai Hongjie","year":"2022","unstructured":"Hongjie Cai, Yue Gao, and Manhua Liu. 2022. Graph transformer geometric learning of brain networks using multimodal MR images for brain age estimation. IEEE Transactions on Medical Imaging 42, 2 (2022), 456\u2013466.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_3_1_12_2","first-page":"15661","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chan Tsai Hor","year":"2023","unstructured":"Tsai Hor Chan, Fernando Julio Cendra, Lan Ma, Guosheng Yin, and Lequan Yu. 2023. Histopathology whole slide image analysis with heterogeneous graph representation learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 15661\u201315670."},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","first-page":"111625","DOI":"10.1016\/j.knosys.2024.111625","article-title":"A novel approach for rumor detection in social platforms: memory-augmented transformer with graph convolutional networks","volume":"292","author":"Chang Qian","year":"2024","unstructured":"Qian Chang, Xia Li, and Zhao Duan. 2024. A novel approach for rumor detection in social platforms: memory-augmented transformer with graph convolutional networks. Knowledge-Based Systems 292 (2024), 111625.","journal-title":"Knowledge-Based Systems"},{"key":"e_1_3_1_14_2","first-page":"3438","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Chen Deli","year":"2020","unstructured":"Deli Chen, Yankai Lin, Wei Li, Peng Li, Jie Zhou, and Xu Sun. 2020. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 3438\u20133445."},{"key":"e_1_3_1_15_2","first-page":"3469","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Chen Dexiong","year":"2022","unstructured":"Dexiong Chen, Leslie O\u2019Bray, and Karsten Borgwardt. 2022. Structure-aware transformer for graph representation learning. In Proceedings of the International Conference on Machine Learning. PMLR, 3469\u20133489."},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"2502","DOI":"10.1145\/3626772.3657971","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Chen Huiyuan","year":"2024","unstructured":"Huiyuan Chen, Zhe Xu, Chin-Chia Michael Yeh, Vivian Lai, Yan Zheng, Minghua Xu, and Hanghang Tong. 2024. Masked graph transformer for large-scale recommendation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2502\u20132506."},{"key":"e_1_3_1_17_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Chen Jinsong","year":"2023","unstructured":"Jinsong Chen, Kaiyuan Gao, Gaichao Li, and Kun He. 2023. NAGphormer: A tokenized graph transformer for node classification in large graphs. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_18_2","volume-title":"Proceedings of the 39th Annual Conference on Neural Information Processing Systems","author":"Chen Jinsong","year":"2025","unstructured":"Jinsong Chen, Chenyang Li, Gaichao Li, John E. Hopcroft, and Kun He. 2025. Rethinking tokenized graph transformers for node classification. In Proceedings of the 39th Annual Conference on Neural Information Processing Systems."},{"issue":"4","key":"e_1_3_1_19_2","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1109\/TBDATA.2024.3524081","article-title":"NAGphormer+: A tokenized graph transformer with neighborhood augmentation for node classification in large graphs","volume":"11","author":"Chen Jinsong","year":"2024","unstructured":"Jinsong Chen, Chang Liu, Kaiyuan Gao, Gaichao Li, and Kun He. 2024. NAGphormer+: A tokenized graph transformer with neighborhood augmentation for node classification in large graphs. IEEE Transactions on Big Data 11, 4 (2024), 2085\u20132098.","journal-title":"IEEE Transactions on Big Data"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","first-page":"85824","DOI":"10.52202\/079017-2725","article-title":"Leveraging contrastive learning for enhanced node representations in tokenized graph transformers","volume":"37","author":"Chen Jinsong","year":"2024","unstructured":"Jinsong Chen, Hanpeng Liu, John Hopcroft, and Kun He. 2024. Leveraging contrastive learning for enhanced node representations in tokenized graph transformers. Advances in Neural Information Processing Systems 37 (2024), 85824\u201385845.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_21_2","first-page":"1725","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Chen Ming","year":"2020","unstructured":"Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, and Yaliang Li. 2020. Simple and deep graph convolutional networks. In Proceedings of the International Conference on Machine Learning (ICML). PMLR, 1725\u20131735."},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1145\/3626772.3657747","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Chen Sirui","year":"2024","unstructured":"Sirui Chen, Jiawei Chen, Sheng Zhou, Bohao Wang, Shen Han, Chanfei Su, Yuqing Yuan, and Can Wang. 2024. SIGformer: Sign-aware graph transformer for recommendation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1274\u20131284."},{"key":"e_1_3_1_23_2","first-page":"16537","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen Shizhe","year":"2022","unstructured":"Shizhe Chen, Pierre-Louis Guhur, Makarand Tapaswi, Cordelia Schmid, and Ivan Laptev. 2022. Think global, act local: Dual-scale graph transformer for vision-and-language navigation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16537\u201316547."},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1145\/3696410.3714547","volume-title":"Proceedings of the ACM on Web Conference 2025","author":"Chen Sirui","year":"2025","unstructured":"Sirui Chen, Shen Han, Jiawei Chen, Binbin Hu, Sheng Zhou, Gang Wang, Yan Feng, Chun Chen, and Can Wang. 2025. Rankformer: A graph transformer for recommendation based on ranking objective. In Proceedings of the ACM on Web Conference 2025. 3037\u20133048."},{"key":"e_1_3_1_25_2","first-page":"15534","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen Sijia","year":"2022","unstructured":"Sijia Chen and Baochun Li. 2022. Multi-modal dynamic graph transformer for visual grounding. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 15534\u201315543."},{"issue":"1","key":"e_1_3_1_26_2","first-page":"i308\u2013i317","article-title":"A gated graph transformer for protein complex structure quality assessment and its performance in CASP15","volume":"39","author":"Chen Xiao","year":"2023","unstructured":"Xiao Chen, Alex Morehead, Jian Liu, and Jianlin Cheng. 2023. A gated graph transformer for protein complex structure quality assessment and its performance in CASP15. Bioinformatics 39, Supplement_1, (2023), i308\u2013i317.","journal-title":"Bioinformatics"},{"key":"e_1_3_1_27_2","first-page":"3962","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Choromanski Krzysztof","year":"2022","unstructured":"Krzysztof Choromanski, Han Lin, Haoxian Chen, Tianyi Zhang, Arijit Sehanobish, Valerii Likhosherstov, Jack Parker-Holder, Tamas Sarlos, Adrian Weller, and Thomas Weingarten. 2022. From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers. In Proceedings of the International Conference on Machine Learning. PMLR, 3962\u20133983."},{"key":"e_1_3_1_28_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Choromanski Krzysztof Marcin","year":"2021","unstructured":"Krzysztof Marcin Choromanski, Valerii Likhosherstov, David Dohan, Xingyou Song, Andreea Gane, Tamas Sarlos, Peter Hawkins, Jared Quincy Davis, Afroz Mohiuddin, Lukasz Kaiser et\u00a0al. 2021. Rethinking attention with performers. In Proceedings of the International Conference on Learning Representations."},{"issue":"1","key":"e_1_3_1_29_2","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/s41524-021-00650-1","article-title":"Atomistic line graph neural network for improved materials property predictions","volume":"7","author":"Choudhary Kamal","year":"2021","unstructured":"Kamal Choudhary and Brian DeCost. 2021. Atomistic line graph neural network for improved materials property predictions. npj Computational Materials 7, 1 (2021), 185.","journal-title":"npj Computational Materials"},{"issue":"2","key":"e_1_3_1_30_2","doi-asserted-by":"crossref","first-page":"e4862","DOI":"10.1002\/pro.4862","article-title":"Flexible protein\u2013protein docking with a multitrack iterative transformer","volume":"33","author":"Chu Lee-Shin","year":"2024","unstructured":"Lee-Shin Chu, Jeffrey A. Ruffolo, Ameya Harmalkar, and Jeffrey J. Gray. 2024. Flexible protein\u2013protein docking with a multitrack iterative transformer. Protein Science 33, 2 (2024), e4862.","journal-title":"Protein Science"},{"key":"e_1_3_1_31_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)","author":"Dai Wei","year":"2023","unstructured":"Wei Dai, Hejie Cui, Xuan Kan, Ying Guo, Sanne van Rooij, and Carl Yang. 2023. Transformer-based hierarchical clustering for brain network analysis. In Proceedings of the 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). 1\u20135."},{"key":"e_1_3_1_32_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Deng Chenhui","year":"2024","unstructured":"Chenhui Deng, Zichao Yue, and Zhiru Zhang. 2024. Polynormer: Polynomial-expressive graph transformer in linear time. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_33_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171\u20134186."},{"issue":"1","key":"e_1_3_1_34_2","doi-asserted-by":"crossref","first-page":"6170","DOI":"10.1038\/s41467-024-49780-2","article-title":"Stability oracle: A structure-based graph-transformer framework for identifying stabilizing mutations","volume":"15","author":"Diaz Daniel J.","year":"2024","unstructured":"Daniel J. Diaz, Chengyue Gong, Jeffrey Ouyang-Zhang, James M. Loy, Jordan Wells, David Yang, Andrew D. Ellington, Alexandros G. Dimakis, and Adam R. Klivans. 2024. Stability oracle: A structure-based graph-transformer framework for identifying stabilizing mutations. Nature Communications 15, 1 (2024), 6170.","journal-title":"Nature Communications"},{"key":"e_1_3_1_35_2","first-page":"9784","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Ding Shuxiao","year":"2023","unstructured":"Shuxiao Ding, Eike Rehder, Lukas Schneider, Marius Cordts, and Juergen Gall. 2023. 3DMOTFormer: Graph transformer for online 3D multi-object tracking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 9784\u20139794."},{"key":"e_1_3_1_36_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et\u00a0al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_37_2","article-title":"A generalization of transformer networks to graphs","author":"Dwivedi Vijay Prakash","year":"2021","unstructured":"Vijay Prakash Dwivedi and Xavier Bresson. 2021. A generalization of transformer networks to graphs. In Proceedings of the AAAI Workshop on Deep Learning on Graphs: Methods and Applications.","journal-title":"Proceedings of the AAAI Workshop on Deep Learning on Graphs: Methods and Applications"},{"key":"e_1_3_1_38_2","volume-title":"Proceedings of the 14th International Conference on Learning Representations","author":"Dwivedi Vijay Prakash","year":"2026","unstructured":"Vijay Prakash Dwivedi, Sri Jaladi, Yangyi Shen, Federico Lopez, Charilaos I. Kanatsoulis, Rishi Puri, Matthias Fey, and Jure Leskovec. 2026. Relational graph transformer. In Proceedings of the 14th International Conference on Learning Representations."},{"key":"e_1_3_1_39_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dwivedi Vijay Prakash","year":"2022","unstructured":"Vijay Prakash Dwivedi, Anh Tuan Luu, Thomas Laurent, Yoshua Bengio, and Xavier Bresson. 2022. Graph neural networks with learnable structural and positional representations. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","first-page":"22326","DOI":"10.52202\/068431-1622","article-title":"Long range graph benchmark","volume":"35","author":"Dwivedi Vijay Prakash","year":"2022","unstructured":"Vijay Prakash Dwivedi, Ladislav Rampasek, Michael Galkin, Ali Parviz, Guy Wolf, Anh Tuan Luu, and Dominique Beaini. 2022. Long range graph benchmark. Advances in Neural Information Processing Systems 35 (2022), 22326\u201322340.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","first-page":"375","DOI":"10.18653\/v1\/2022.emnlp-main.26","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Edwards Carl","year":"2022","unstructured":"Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, and Heng Ji. 2022. Translation between molecules and natural language. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates, 375\u2013413."},{"key":"e_1_3_1_42_2","first-page":"2831","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","author":"Fan Yujie","year":"2021","unstructured":"Yujie Fan, Mingxuan Ju, Shifu Hou, Yanfang Ye, Wenqiang Wan, Kui Wang, Yinming Mei, and Qi Xiong. 2021. Heterogeneous temporal graph transformer: An intelligent system for evolving android malware detection. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2831\u20132839."},{"key":"e_1_3_1_43_2","first-page":"1537","volume-title":"Proceedings of the 2025 IEEE 41st International Conference on Data Engineering (ICDE)","author":"Fang Shuheng","year":"2025","unstructured":"Shuheng Fang, Kangfei Zhao, Yu Rong, Jeffrey Xu Yu, and Zhixun Li. 2025. All-in-One: Heterogeneous interaction modeling for cold-start rating prediction. In Proceedings of the 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE Computer Society, 1537\u20131550."},{"key":"e_1_3_1_44_2","volume-title":"Proceedings of the 14th International Conference on Learning Representations","author":"Feng Jinjia","year":"2026","unstructured":"Jinjia Feng, Zhewei Wei, Taifeng Wang, and Zongyang Qiu. 2026. TetraGT: Tetrahedral geometry-driven explicit token interactions with graph transformer for molecular representation learning. In Proceedings of the 14th International Conference on Learning Representations."},{"key":"e_1_3_1_45_2","first-page":"9938","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Feng Shikun","year":"2023","unstructured":"Shikun Feng, Yuyan Ni, Yanyan Lan, Zhi-Ming Ma, and Wei-Ying Ma. 2023. Fractional denoising for 3D molecular pre-training. In Proceedings of the International Conference on Machine Learning. PMLR, 9938\u20139961."},{"key":"e_1_3_1_46_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Fu Dongqi","year":"2024","unstructured":"Dongqi Fu, Zhigang Hua, Yan Xie, Jin Fang, Si Zhang, Kaan Sancak, Hao Wu, Andrey Malevich, Jingrui He, and Bo Long. 2024. VCR-Graphormer: A mini-batch graph transformer via virtual connections. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_47_2","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Fuchs Fabian B.","year":"2020","unstructured":"Fabian B. Fuchs, Daniel E. Worrall, Volker Fischer, and Max Welling. 2020. SE(3)-Transformers: 3D roto-translation equivariant attention networks. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_1_48_2","doi-asserted-by":"crossref","first-page":"108339","DOI":"10.1016\/j.compbiomed.2024.108339","article-title":"GraphormerDTI: A graph transformer-based approach for drug-target interaction prediction","volume":"173","author":"Gao Mengmeng","year":"2024","unstructured":"Mengmeng Gao, Daokun Zhang, Yi Chen, Yiwen Zhang, Zhikang Wang, Xiaoyu Wang, Shanshan Li, Yuming Guo, Geoffrey I. Webb, Anh T.N. Nguyen, et\u00a0al. 2024. GraphormerDTI: A graph transformer-based approach for drug-target interaction prediction. Computers in Biology and Medicine 173 (2024), 108339.","journal-title":"Computers in Biology and Medicine"},{"key":"e_1_3_1_49_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Gao Zhangyang","year":"2024","unstructured":"Zhangyang Gao, Daize Dong, Cheng Tan, Jun Xia, Bozhen Hu, and Stan Z. Li. 2024. A graph is worth \\(K\\) words: Euclideanizing graph using pure transformer. In Proceedings of the 41st International Conference on Machine Learning."},{"key":"e_1_3_1_50_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Gasteiger Johannes","year":"2019","unstructured":"Johannes Gasteiger, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2019. Predict then propagate: Graph neural networks meet personalized pagerank. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_1_51_2","first-page":"1243","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Gehring Jonas","year":"2017","unstructured":"Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, and Yann N. Dauphin. 2017. Convolutional sequence to sequence learning. In Proceedings of the International Conference on Machine Learning. PMLR, 1243\u20131252."},{"key":"e_1_3_1_52_2","first-page":"1263","volume-title":"Proceedings of the InternationAl Conference on Machine Learning","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. 2017. Neural message passing for quantum chemistry. In Proceedings of the InternationAl Conference on Machine Learning. PMLR, 1263\u20131272."},{"key":"e_1_3_1_53_2","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1145\/3770854.3785701","volume-title":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1","author":"Gr\u00f6tschla Florian","year":"2026","unstructured":"Florian Gr\u00f6tschla, Jiaqing Xie, and Roger Wattenhofer. 2026. Benchmarking positional encodings for GNNs and graph transformers. In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1. 2663\u20132674."},{"key":"e_1_3_1_54_2","first-page":"855","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916)","author":"Grover Aditya","year":"2016","unstructured":"Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916). ACM, New York, NY, USA, 855\u2013864."},{"key":"e_1_3_1_55_2","volume-title":"Proceedings of the 1st Conference on Language Modeling","author":"Gu Albert","year":"2024","unstructured":"Albert Gu and Tri Dao. 2024. Mamba: Linear-time sequence modeling with selective state spaces. In Proceedings of the 1st Conference on Language Modeling."},{"issue":"7","key":"e_1_3_1_56_2","doi-asserted-by":"crossref","first-page":"btad410","DOI":"10.1093\/bioinformatics\/btad410","article-title":"Hierarchical graph transformer with contrastive learning for protein function prediction","volume":"39","author":"Gu Zhonghui","year":"2023","unstructured":"Zhonghui Gu, Xiao Luo, Jiaxiao Chen, Minghua Deng, and Luhua Lai. 2023. Hierarchical graph transformer with contrastive learning for protein function prediction. Bioinformatics 39, 7 (2023), btad410.","journal-title":"Bioinformatics"},{"issue":"11","key":"e_1_3_1_57_2","first-page":"1","article-title":"A survey of geometric graph neural networks: Data structures, models and applications","volume":"19","author":"Han Jiaqi","year":"2025","unstructured":"Jiaqi Han, Jiacheng Cen, Liming Wu, Zongzhao Li, Xiangzhe Kong, Rui Jiao, Ziyang Yu, Tingyang Xu, Fandi Wu, Zihe Wang, et\u00a0al. 2025. A survey of geometric graph neural networks: Data structures, models and applications. Frontiers of Computer Science 19, 11 (2025), 1\u201338.","journal-title":"Frontiers of Computer Science"},{"key":"e_1_3_1_58_2","series-title":"Proceedings of Machine Learning Research","first-page":"22792","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","volume":"267","author":"He Mingzhen","year":"2025","unstructured":"Mingzhen He, Ruikai Yang, Hanling Tian, Youmei Qiu, and Xiaolin Huang. 2025. Primphormer: Efficient graph transformers with primal representations. In Proceedings of the 42nd International Conference on Machine Learning. Aarti Singh, Maryam Fazel, Daniel Hsu, Simon Lacoste-Julien, Felix Berkenkamp, Tegan Maharaj, Kiri Wagstaff, and Jerry Zhu (Eds.), Proceedings of Machine Learning Research, Vol. 267, PMLR, 22792\u201322815."},{"key":"e_1_3_1_59_2","first-page":"12724","volume-title":"Proceedings of the International Conference on Machine Learning","author":"He Xiaoxin","year":"2023","unstructured":"Xiaoxin He, Bryan Hooi, Thomas Laurent, Adam Perold, Yann LeCun, and Xavier Bresson. 2023. A generalization of vit\/mlp-mixer to graphs. In Proceedings of the International Conference on Machine Learning. PMLR, 12724\u201312745."},{"key":"e_1_3_1_60_2","first-page":"189","volume-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics","author":"He Xuehai","year":"2023","unstructured":"Xuehai He and Xin Wang. 2023. Multimodal graph transformer for multimodal question answering. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 189\u2013200."},{"key":"e_1_3_1_61_2","first-page":"22096","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Hebert Liam","year":"2024","unstructured":"Liam Hebert, Gaurav Sahu, Yuxuan Guo, Nanda Kishore Sreenivas, Lukasz Golab, and Robin Cohen. 2024. Multi-modal discussion transformer: Integrating text, images and graph transformers to detect hate speech on social media. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 22096\u201322104."},{"issue":"4","key":"e_1_3_1_62_2","doi-asserted-by":"crossref","first-page":"lqae150","DOI":"10.1093\/nargab\/lqae150","article-title":"Bilingual language model for protein sequence and structure","volume":"6","author":"Heinzinger Michael","year":"2024","unstructured":"Michael Heinzinger, Konstantin Weissenow, Joaquin\u00c2 Gomez Sanchez, Adrian Henkel, Milot Mirdita, Martin Steinegger, and Burkhard Rost. 2024. Bilingual language model for protein sequence and structure. NAR Genomics and Bioinformatics 6, 4 (112024), lqae150.","journal-title":"NAR Genomics and Bioinformatics"},{"key":"e_1_3_1_63_2","first-page":"8946","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Hsu Chloe","year":"2022","unstructured":"Chloe Hsu, Robert Verkuil, Jason Liu, Zeming Lin, Brian Hie, Tom Sercu, Adam Lerer, and Alexander Rives. 2022. Learning inverse folding from millions of predicted structures. In Proceedings of the International Conference on Machine Learning. PMLR, 8946\u20138970."},{"key":"e_1_3_1_64_2","first-page":"2809","volume-title":"Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Hu Jinlong","year":"2023","unstructured":"Jinlong Hu, Yangmin Huang, and Shoubin Dong. 2023. Transformer and snowball graph convolution learning for brain functional network analysis. In Proceedings of the 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2809\u20132816."},{"key":"e_1_3_1_65_2","volume-title":"Proceedings of the 14th International Conference on Learning Representations","author":"Hu Yuting","year":"2026","unstructured":"Yuting Hu, Tarek Mohamed, Chenhui Xu, Hua Xiang, Hussam Amrouch, Gi-Joon Nam, and Jinjun Xiong. 2026. Si-GT: Fast interconnect signal integrity analysis for integrated circuit design via graph transformers. In Proceedings of the 14th International Conference on Learning Representations."},{"key":"e_1_3_1_66_2","first-page":"33","volume-title":"Proceedings of the Learning on Graphs Conference","author":"Hua Chenqing","year":"2024","unstructured":"Chenqing Hua, Sitao Luan, Minkai Xu, Zhitao Ying, Jie Fu, Stefano Ermon, and Doina Precup. 2024. Mudiff: Unified diffusion for complete molecule generation. In Proceedings of the Learning on Graphs Conference. PMLR, 33\u20131."},{"key":"e_1_3_1_67_2","first-page":"4302","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Huang Han","year":"2023","unstructured":"Han Huang, Leilei Sun, Bowen Du, and Weifeng Lv. 2023. Conditional diffusion based on discrete graph structures for molecular graph generation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 4302\u20134311."},{"issue":"9","key":"e_1_3_1_68_2","doi-asserted-by":"crossref","first-page":"11857","DOI":"10.1109\/TNNLS.2024.3416328","article-title":"Learning joint 2-D and 3-D graph diffusion models for complete molecule generation","volume":"35","author":"Huang Han","year":"2024","unstructured":"Han Huang, Leilei Sun, Bowen Du, and Weifeng Lv. 2024. Learning joint 2-D and 3-D graph diffusion models for complete molecule generation. IEEE Transactions on Neural Networks and Learning Systems 35, 9 (2024), 11857\u201311871.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_69_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Huang Yinan","year":"2024","unstructured":"Yinan Huang, William Lu, Joshua Robinson, Yu Yang, Muhan Zhang, Stefanie Jegelka, and Pan Li. 2024. On the stability of expressive positional encodings for graphs. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_70_2","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1145\/3534678.3539296","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Hussain Md. Shamim","year":"2022","unstructured":"Md. Shamim Hussain, Mohammed J. Zaki, and Dharmashankar Subramanian. 2022. Global self-attention as a replacement for graph convolution. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 655\u2013665."},{"key":"e_1_3_1_71_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Hussain Md. Shamim","year":"2024","unstructured":"Md. Shamim Hussain, Mohammed J. Zaki, and Dharmashankar Subramanian. 2024. Triplet interaction improves graph transformers: Accurate molecular graph learning with triplet graph transformers. In Proceedings of the 41st International Conference on Machine Learning."},{"key":"e_1_3_1_72_2","first-page":"2375","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Ivanovic Boris","year":"2019","unstructured":"Boris Ivanovic and Marco Pavone. 2019. The trajectron: Probabilistic multi-agent trajectory modeling with dynamic spatiotemporal graphs. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2375\u20132384."},{"issue":"1","key":"e_1_3_1_73_2","doi-asserted-by":"crossref","first-page":"5663","DOI":"10.1038\/s41598-023-31612-w","article-title":"Graph-BERT and language model-based framework for protein\u2013protein interaction identification","volume":"13","author":"Jha Kanchan","year":"2023","unstructured":"Kanchan Jha, Sourav Karmakar, and Sriparna Saha. 2023. Graph-BERT and language model-based framework for protein\u2013protein interaction identification. Scientific Reports 13, 1 (2023), 5663.","journal-title":"Scientific Reports"},{"key":"e_1_3_1_74_2","volume-title":"Proceedings of the 38th Annual Conference on Neural Information Processing Systems","author":"Ji Xiaohong","year":"2024","unstructured":"Xiaohong Ji, Zhen Wang, Zhifeng Gao, Hang Zheng, Linfeng Zhang, Guolin Ke, and Weinan E. 2024. Exploring molecular pretraining model at scale. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_75_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Jin Bowen","year":"2023","unstructured":"Bowen Jin, Yu Zhang, Yu Meng, and Jiawei Han. 2023. Edgeformers: Graph-empowered transformers for representation learning on textual-edge networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_76_2","first-page":"1020","volume-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Jin Bowen","year":"2023","unstructured":"Bowen Jin, Yu Zhang, Qi Zhu, and Jiawei Han. 2023. Heterformer: Transformer-based deep node representation learning on heterogeneous text-rich networks. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1020\u20131031."},{"key":"e_1_3_1_77_2","doi-asserted-by":"crossref","first-page":"2860","DOI":"10.1145\/3696410.3714596","volume-title":"Proceedings of the ACM on Web Conference 2025","author":"Jin Di","year":"2025","unstructured":"Di Jin, Cuiying Huo, Jiayi Shi, Dongxiao He, Jianguo Wei, and Philip S. Yu. 2025. LLGformer: Learnable long-range graph transformer for traffic flow prediction. In Proceedings of the ACM on Web Conference 2025. 2860\u20132871."},{"key":"e_1_3_1_78_2","first-page":"8114","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Jin Di","year":"2023","unstructured":"Di Jin, Jiayi Shi, Rui Wang, Yawen Li, Yuxiao Huang, and Yu-Bin Yang. 2023. Trafformer: Unify time and space in traffic prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 8114\u20138122."},{"key":"e_1_3_1_79_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Jing Bowen","year":"2021","unstructured":"Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael John Lamarre Townshend, and Ron Dror. 2021. Learning from protein structure with geometric vector perceptrons. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_80_2","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Kan Xuan","year":"2022","unstructured":"Xuan Kan, Wei Dai, Hejie Cui, Zilong Zhang, Ying Guo, and Carl Yang. 2022. Brain network transformer. In Proceedings of the International Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_81_2","first-page":"8783","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Khoo Ling Min Serena","year":"2020","unstructured":"Ling Min Serena Khoo, Hai Leong Chieu, Zhong Qian, and Jing Jiang. 2020. Interpretable rumor detection in microblogs by attending to user interactions. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 8783\u20138790."},{"key":"e_1_3_1_82_2","first-page":"14582","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Kim Jinwoo","year":"2022","unstructured":"Jinwoo Kim, Dat Nguyen, Seonwoo Min, Sungjun Cho, Moontae Lee, Honglak Lee, and Seunghoon Hong. 2022. Pure transformers are powerful graph learners. In Proceedings of the International Conference on Neural Information Processing Systems. 14582\u201314595."},{"key":"e_1_3_1_83_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations, ICLR 2017,","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations, ICLR 2017,."},{"key":"e_1_3_1_84_2","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume":"34","author":"Kreuzer Devin","year":"2021","unstructured":"Devin Kreuzer, Dominique Beaini, Will Hamilton, Vincent Letourneau, and Prudencio Tossou. 2021. Rethinking graph transformers with spectral attention. Advances in Neural Information Processing Systems 34 (2021), 21618\u201321629.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_85_2","first-page":"1680","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Li Chaoliu","year":"2023","unstructured":"Chaoliu Li, Lianghao Xia, Xubin Ren, Yaowen Ye, Yong Xu, and Chao Huang. 2023. Graph transformer for recommendation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1680\u20131689."},{"key":"e_1_3_1_86_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Li Hongkang","year":"2024","unstructured":"Hongkang Li, Meng Wang, Tengfei Ma, Sijia Liu, Zaixi Zhang, and Pin-Yu Chen. 2024. What improves the generalization of graph transformers? A theoretical dive into the self-attention and positional encoding. In Proceedings of the 41st International Conference on Machine Learning. Article 1157, 46 pages."},{"key":"e_1_3_1_87_2","first-page":"857","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Li Han","year":"2022","unstructured":"Han Li, Dan Zhao, and Jianyang Zeng. 2022. KPGT: Knowledge-guided pre-training of graph transformer for molecular property prediction. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 857\u2013867."},{"key":"e_1_3_1_88_2","first-page":"30306","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","volume":"36","author":"Li Zhixun","year":"2023","unstructured":"Zhixun Li, Liang Wang, Xin Sun, Yifan Luo, Yanqiao Zhu, Dingshuo Chen, Yingtao Luo, Xiangxin Zhou, Qiang Liu, Shu Wu et\u00a0al. 2023. GSLB: The graph structure learning benchmark. In Proceedings of the International Conference on Neural Information Processing Systems, Vol. 36. 30306\u201330318."},{"key":"e_1_3_1_89_2","volume-title":"Proceedings of the 39th Annual Conference on Neural Information Processing Systems","author":"Liao Ningyi","year":"2025","unstructured":"Ningyi Liao, Zihao Yu, Siqiang Luo, and Gao Cong. 2025. HubGT: Fast graph transformer with decoupled hierarchy labeling. In Proceedings of the 39th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_90_2","unstructured":"Yi-Lun Liao Alexander J. Hoffman Sabrina C. Shen Alexandre Duval Sam Walton Norwood and Tess Smidt. 2026. EquiformerV3: Scaling efficient expressive and general se (3)-equivariant graph attention transformers. arXiv preprint arXiv:2604.09130. Retrieved from https:\/\/arxiv.org\/abs\/2604.09130"},{"key":"e_1_3_1_91_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Liao Yi-Lun","year":"2023","unstructured":"Yi-Lun Liao and Tess Smidt. 2023. Equiformer: Equivariant graph attention transformer for 3D atomistic graphs. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_92_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Liao Yi-Lun","year":"2024","unstructured":"Yi-Lun Liao, Brandon Wood, Abhishek Das, and Tess Smidt. 2024. EquiformerV2: Improved equivariant transformer for scaling to higher-degree representations. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_93_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Lim Derek","year":"2023","unstructured":"Derek Lim, Joshua David Robinson, Lingxiao Zhao, Tess Smidt, Suvrit Sra, Haggai Maron, and Stefanie Jegelka. 2023. Sign and basis invariant networks for spectral graph representation learning. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_94_2","first-page":"12939","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Lin Kevin","year":"2021","unstructured":"Kevin Lin, Lijuan Wang, and Zicheng Liu. 2021. Mesh graphormer. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 12939\u201312948."},{"issue":"6637","key":"e_1_3_1_95_2","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin Zeming","year":"2023","unstructured":"Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Robert Verkuil, Ori Kabeli, Yaniv Shmueli, et\u00a0al. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 6637 (2023), 1123\u20131130.","journal-title":"Science"},{"key":"e_1_3_1_96_2","volume-title":"Proceedings of the 38th Annual Conference on Neural Information Processing Systems","author":"Liu Gang","year":"2024","unstructured":"Gang Liu, Jiaxin Xu, Tengfei Luo, and Meng Jiang. 2024. Graph diffusion transformers for multi-conditional molecular generation. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems."},{"issue":"5","key":"e_1_3_1_97_2","doi-asserted-by":"crossref","first-page":"bbac162","DOI":"10.1093\/bib\/bbac162","article-title":"Improved drug\u2013target interaction prediction with intermolecular graph transformer","volume":"23","author":"Liu Siyuan","year":"2022","unstructured":"Siyuan Liu, Yusong Wang, Yifan Deng, Liang He, Bin Shao, Jian Yin, Nanning Zheng, Tie-Yan Liu, and Tong Wang. 2022. Improved drug\u2013target interaction prediction with intermolecular graph transformer. Briefings in Bioinformatics 23, 5 (2022), bbac162.","journal-title":"Briefings in Bioinformatics"},{"key":"e_1_3_1_98_2","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Liu Xiao","year":"2022","unstructured":"Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen, Jiezhong Qiu, Mengdi Zhang, Wei Wu, Yuxiao Dong, and Jie Tang. 2022. Mask and reason: Pre-training knowledge graph transformers for complex logical queries. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining."},{"key":"e_1_3_1_99_2","first-page":"2853","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Liu Yong","year":"2021","unstructured":"Yong Liu, Susen Yang, Chenyi Lei, Guoxin Wang, Haihong Tang, Juyong Zhang, Aixin Sun, and Chunyan Miao. 2021. Pre-training graph transformer with multimodal side information for recommendation. In Proceedings of the 29th ACM International Conference on Multimedia. 2853\u20132861."},{"key":"e_1_3_1_100_2","first-page":"15623","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023","author":"Liu Zhiyuan","year":"2023","unstructured":"Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, and Tat-Seng Chua. 2023. MolCA: Molecular graph-language modeling with cross-modal projector and uni-modal adapter. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023. 15623\u201315638."},{"issue":"1","key":"e_1_3_1_101_2","doi-asserted-by":"crossref","first-page":"7104","DOI":"10.1038\/s41467-024-51321-w","article-title":"Data-driven quantum chemical property prediction leveraging 3D conformations with uni-mol+","volume":"15","author":"Lu Shuqi","year":"2024","unstructured":"Shuqi Lu, Zhifeng Gao, Di He, Linfeng Zhang, and Guolin Ke. 2024. Data-driven quantum chemical property prediction leveraging 3D conformations with uni-mol+. Nature Communications 15, 1 (2024), 7104.","journal-title":"Nature Communications"},{"key":"e_1_3_1_102_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Luo Shengjie","year":"2023","unstructured":"Shengjie Luo, Tianlang Chen, Yixian Xu, Shuxin Zheng, Tie-Yan Liu, Liwei Wang, and Di He. 2023. One transformer can understand both 2D & 3D molecular data. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_103_2","first-page":"57150","article-title":"Enhancing graph transformers with hierarchical distance structural encoding","volume":"37","author":"Luo Yuankai","year":"2024","unstructured":"Yuankai Luo, Hongkang Li, Lei Shi, and Xiao-Ming Wu. 2024. Enhancing graph transformers with hierarchical distance structural encoding. Advances in Neural Information Processing Systems 37 (2024), 57150\u201357182.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_104_2","first-page":"4035","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Lv Changsheng","year":"2024","unstructured":"Changsheng Lv, Mengshi Qi, Xia Li, Zhengyuan Yang, and Huadong Ma. 2024. SGFormer: Semantic graph transformer for point cloud-based 3D scene graph generation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 4035\u20134043."},{"issue":"9","key":"e_1_3_1_105_2","first-page":"11989","article-title":"SSAGCN: Social soft attention graph convolution network for pedestrian trajectory prediction","volume":"35","author":"Lv Pei","year":"2023","unstructured":"Pei Lv, Wentong Wang, Yunxin Wang, Yuzhen Zhang, Mingliang Xu, and Changsheng Xu. 2023. SSAGCN: Social soft attention graph convolution network for pedestrian trajectory prediction. IEEE Transactions on Neural Networks and Learning Systems, 35, 9 (2023), 11989\u201312003.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_1_106_2","first-page":"23321","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ma Liheng","year":"2023","unstructured":"Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, and Ser-Nam Lim. 2023. Graph inductive biases in transformers without message passing. In Proceedings of the International Conference on Machine Learning. PMLR, 23321\u201323337."},{"key":"e_1_3_1_107_2","first-page":"6120","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"33","author":"Ma Yuexin","year":"2019","unstructured":"Yuexin Ma, Xinge Zhu, Sibo Zhang, Ruigang Yang, Wenping Wang, and Dinesh Manocha. 2019. Trafficpredict: Trajectory prediction for heterogeneous traffic-agents. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 6120\u20136127."},{"key":"e_1_3_1_108_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Mao Haitao","year":"2024","unstructured":"Haitao Mao, Zhikai Chen, Wenzhuo Tang, Jianan Zhao, Yao Ma, Tong Zhao, Neil Shah, Mikhail Galkin, and Jiliang Tang. 2024. Position: Graph foundation models are already here. In Proceedings of the 41st International Conference on Machine Learning."},{"key":"e_1_3_1_109_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Maron Haggai","year":"2019","unstructured":"Haggai Maron, Heli Ben-Hamu, Nadav Shamir, and Yaron Lipman. 2019. Invariant and equivariant graph networks. In Proceedings of the International Conference on Learning Representations."},{"issue":"1","key":"e_1_3_1_110_2","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s40537-023-00841-1","article-title":"Gct-TTE: Graph convolutional transformer for travel time estimation","volume":"11","author":"Mashurov Vladimir","year":"2024","unstructured":"Vladimir Mashurov, Vaagn Chopuryan, Vadim Porvatov, Arseny Ivanov, and Natalia Semenova. 2024. Gct-TTE: Graph convolutional transformer for travel time estimation. Journal of Big Data 11, 1 (2024), 15.","journal-title":"Journal of Big Data"},{"key":"e_1_3_1_111_2","unstructured":"Lukasz Maziarka Tomasz Danel Slawomir Mucha Krzysztof Rataj Jacek Tabor and Stanislaw Jastrzebski. 2020. Molecule attention transformer. arXiv preprint arXiv:2002.08264. Retrieved from https:\/\/arxiv.org\/abs\/2002.08264"},{"issue":"1","key":"e_1_3_1_112_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/s13321-023-00789-7","article-title":"Relative molecule self-attention transformer","volume":"16","author":"Maziarka Lukasz","year":"2024","unstructured":"Lukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gainski, Jacek Tabor, Igor Podolak, Pawel Morkisz, and Stanislaw Jastrzkebski. 2024. Relative molecule self-attention transformer. Journal of Cheminformatics 16, 1 (2024), 3.","journal-title":"Journal of Cheminformatics"},{"key":"e_1_3_1_113_2","unstructured":"Gr\u00e9goire Mialon Dexiong Chen Margot Selosse and Julien Mairal. 2021. GraphiT: Encoding graph structure in transformers. arXiv preprint arXiv:2106.05667. Retrieved from https:\/\/arxiv.org\/abs\/2106.05667"},{"key":"e_1_3_1_114_2","unstructured":"Erxue Min Runfa Chen Yatao Bian Tingyang Xu Kangfei Zhao Wenbing Huang Peilin Zhao Junzhou Huang Sophia Ananiadou and Yu Rong. 2022. Transformer for graphs: An overview from architecture perspective. arXiv preprint arXiv:2202.08455. Retrieved from https:\/\/arxiv.org\/abs\/2202.08455"},{"key":"e_1_3_1_115_2","first-page":"353","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Min Erxue","year":"2022","unstructured":"Erxue Min, Yu Rong, Tingyang Xu, Yatao Bian, Da Luo, Kangyi Lin, Junzhou Huang, Sophia Ananiadou, and Peilin Zhao. 2022. Neighbour interaction based click-through rate prediction via graph-masked transformer. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval. 353\u2013362."},{"key":"e_1_3_1_116_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Morehead Alex","year":"2022","unstructured":"Alex Morehead, Chen Chen, and Jianlin Cheng. 2022. Geometric transformers for protein interface contact prediction. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_117_2","first-page":"4602","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"33","author":"Morris Christopher","year":"2019","unstructured":"Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, and Martin Grohe. 2019. Weisfeiler and leman go neural: Higher-order graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 4602\u20134609."},{"key":"e_1_3_1_118_2","article-title":"Attending to graph transformers","author":"M\u00fcller Luis","year":"2024","unstructured":"Luis M\u00fcller, Mikhail Galkin, Christopher Morris, and Ladislav Rampasek. 2024. Attending to graph transformers. Transactions on Machine Learning Research (2024).","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_1_119_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"M\u00fcller Luis","year":"2024","unstructured":"Luis M\u00fcller and Christopher Morris. 2024. Aligning transformers with Weisfeiler-Leman. In Proceedings of the 41st International Conference on Machine Learning."},{"key":"e_1_3_1_120_2","first-page":"11547","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Nakhli Ramin","year":"2023","unstructured":"Ramin Nakhli, Puria Azadi Moghadam, Haoyang Mi, Hossein Farahani, Alexander Baras, Blake Gilks, and Ali Bashashati. 2023. Sparse multi-modal graph transformer with shared-context processing for representation learning of giga-pixel images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11547\u201311557."},{"key":"e_1_3_1_121_2","volume-title":"Proceedings of the 14th International Conference on Learning Representations","author":"Nguyen Duy Minh Ho","year":"2026","unstructured":"Duy Minh Ho Nguyen, Trung Quoc Nguyen, Ha Thi Hong Le, Mai Thanh Nhat Truong, TrungTin Nguyen, Nhat Ho, Khoa D. Doan, Duy Duong-Tran, Li Shen, Daniel Sonntag, et\u00a0al. 2026. FACET: A fragment-aware conformer ensemble transformer. In Proceedings of the 14th International Conference on Learning Representations."},{"key":"e_1_3_1_122_2","doi-asserted-by":"crossref","first-page":"111310","DOI":"10.1016\/j.knosys.2023.111310","article-title":"Portable graph-based rumour detection against multi-modal heterophily","volume":"284","author":"Nguyen Thanh Tam","year":"2024","unstructured":"Thanh Tam Nguyen, Zhao Ren, Thanh Toan Nguyen, Jun Jo, Quoc Viet Hung Nguyen, and Hongzhi Yin. 2024. Portable graph-based rumour detection against multi-modal heterophily. Knowledge-Based Systems 284 (2024), 111310.","journal-title":"Knowledge-Based Systems"},{"key":"e_1_3_1_123_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Ni Yuyan","year":"2024","unstructured":"Yuyan Ni, Shikun Feng, Wei-Ying Ma, Zhi-Ming Ma, and Yanyan Lan. 2024. Sliced denoising: A physics-informed molecular pre-training method. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_124_2","doi-asserted-by":"crossref","first-page":"1992","DOI":"10.1145\/3583780.3614769","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","author":"Pahuja Vardaan","year":"2023","unstructured":"Vardaan Pahuja, Boshi Wang, Hugo Latapie, Jayanth Srinivasa, and Yu Su. 2023. A retrieve-and-read framework for knowledge graph link prediction. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. ACM, New York, NY, USA, 1992\u20132002. DOI:10.1145\/3583780.3614769"},{"key":"e_1_3_1_125_2","volume-title":"Proceedings of the 13th International Conference on Learning Representations","author":"Peng Ciyuan","year":"2025","unstructured":"Ciyuan Peng, Yuelong Huang, Qichao Dong, Shuo Yu, Feng Xia, Chengqi Zhang, and Yaochu Jin. 2025. Biologically plausible brain graph transformer. In Proceedings of the 13th International Conference on Learning Representations."},{"issue":"4","key":"e_1_3_1_126_2","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1039\/D4DD00339J","article-title":"GraphXForm: Graph transformer for computer-aided molecular design","volume":"4","author":"Pirnay Jonathan","year":"2025","unstructured":"Jonathan Pirnay, Jan G. Rittig, Alexander B. Wolf, Martin Grohe, Jakob Burger, Alexander Mitsos, and Dominik G. Grimm. 2025. GraphXForm: Graph transformer for computer-aided molecular design. Digital Discovery 4, 4 (2025), 1052\u20131065.","journal-title":"Digital Discovery"},{"key":"e_1_3_1_127_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Poulain Raphael","year":"2024","unstructured":"Raphael Poulain and Rahmatollah Beheshti. 2024. Graph transformers on EHRs: Better representation improves downstream performance. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_128_2","volume-title":"Proceedings of the 39th Annual Conference on Neural Information Processing Systems","author":"Quan Le Viet","year":"2025","unstructured":"Le Viet Quan and Viet Cuong Ta. 2025. Pseudo-Riemannian graph transformer. In Proceedings of the 39th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_129_2","first-page":"14501","article-title":"Recipe for a general, powerful, scalable graph transformer","volume":"35","author":"Rampavsek Ladislav","year":"2022","unstructured":"Ladislav Rampavsek, Michael Galkin, Vijay Prakash Dwivedi, Anh Tuan Luu, Guy Wolf, and Dominique Beaini. 2022. Recipe for a general, powerful, scalable graph transformer. Advances in Neural Information Processing Systems 35 (2022), 14501\u201314515.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_130_2","volume-title":"Advances in Neural Information Processing Systems 33","author":"Rong Yu","year":"2020","unstructured":"Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, and Junzhou Huang. 2020. Self-supervised graph transformer on large-scale molecular data. In Advances in Neural Information Processing Systems 33."},{"key":"e_1_3_1_131_2","volume-title":"Proceedings of the International Conference on Learning Representations, ICLR 2020","author":"Rong Yu","year":"2020","unstructured":"Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2020. DropEdge: Towards deep graph convolutional networks on node classification. In Proceedings of the International Conference on Learning Representations, ICLR 2020."},{"key":"e_1_3_1_132_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Rosenbluth Eran","year":"2024","unstructured":"Eran Rosenbluth, Jan T\u00f6nshoff, Martin Ritzert, Berke Kisin, and Martin Grohe. 2024. Distinguished in uniform: Self-attention vs. virtual nodes. In Proceedings of the 12th International Conference on Learning Representations."},{"issue":"15","key":"e_1_3_1_133_2","doi-asserted-by":"crossref","first-page":"10691","DOI":"10.1021\/acs.jmedchem.2c00991","article-title":"Boosting protein\u2013ligand binding pose prediction and virtual screening based on residue\u2013atom distance likelihood potential and graph transformer","volume":"65","author":"Shen Chao","year":"2022","unstructured":"Chao Shen, Xujun Zhang, Yafeng Deng, Junbo Gao, Dong Wang, Lei Xu, Peichen Pan, Tingjun Hou, and Yu Kang. 2022. Boosting protein\u2013ligand binding pose prediction and virtual screening based on residue\u2013atom distance likelihood potential and graph transformer. Journal of Medicinal Chemistry 65, 15 (2022), 10691\u201310706.","journal-title":"Journal of Medicinal Chemistry"},{"key":"e_1_3_1_134_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Shi Han","year":"2022","unstructured":"Han Shi, Jiahui Gao, Hang Xu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong, Stephen M. S. Lee, and James Kwok. 2022. Revisiting over-smoothing in bert from the perspective of graph. In Proceedings of the International Conference on Learning Representations."},{"issue":"12","key":"e_1_3_1_135_2","doi-asserted-by":"crossref","first-page":"3871","DOI":"10.1109\/TMI.2023.3313252","article-title":"MG-trans: Multi-scale graph transformer with information bottleneck for whole slide image classification","volume":"42","author":"Shi Jiangbo","year":"2023","unstructured":"Jiangbo Shi, Lufei Tang, Zeyu Gao, Yang Li, Chunbao Wang, Tieliang Gong, Chen Li, and Huazhu Fu. 2023. MG-trans: Multi-scale graph transformer with information bottleneck for whole slide image classification. IEEE Transactions on Medical Imaging 42, 12 (2023), 3871\u20133883.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_3_1_136_2","first-page":"341","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Shi Zhan","year":"2024","unstructured":"Zhan Shi, Jingwei Zhang, Jun Kong, and Fusheng Wang. 2024. Integrative graph-transformer framework for histopathology whole slide image representation and classification. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 341\u2013350."},{"key":"e_1_3_1_137_2","volume-title":"Proceedings of the 38th Annual Conference on Neural Information Processing Systems","author":"Shirzad Hamed","year":"2024","unstructured":"Hamed Shirzad, Honghao Lin, Balaji Venkatachalam, Ameya Velingker, David Woodruff, and Danica J. Sutherland. 2024. Even sparser graph transformers. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_138_2","first-page":"31613","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Shirzad Hamed","year":"2023","unstructured":"Hamed Shirzad, Ameya Velingker, Balaji Venkatachalam, Danica J. Sutherland, and Ali Kemal Sinop. 2023. Exphormer: Sparse transformers for graphs. In Proceedings of the International Conference on Machine Learning. PMLR, 31613\u201331632."},{"key":"e_1_3_1_139_2","doi-asserted-by":"crossref","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","article-title":"Roformer: Enhanced transformer with rotary position embedding","volume":"568","author":"Su Jianlin","year":"2024","unstructured":"Jianlin Su, Murtadha Ahmed, Yu Lu, Shengfeng Pan, Wen Bo, and Yunfeng Liu. 2024. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568 (2024), 127063.","journal-title":"Neurocomputing"},{"key":"e_1_3_1_140_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Su Jin","year":"2024","unstructured":"Jin Su, Chenchen Han, Yuyang Zhou, Junjie Shan, Xibin Zhou, and Fajie Yuan. 2024. SaProt: Protein language modeling with structure-aware vocabulary. In Proceedings of the 12th International Conference on Learning Representations."},{"issue":"44","key":"e_1_3_1_141_2","doi-asserted-by":"crossref","first-page":"30707","DOI":"10.1039\/D4TA04495A","article-title":"CrysGraphFormer: An equivariant graph transformer for prediction of lattice thermal conductivity with interpretability","volume":"12","author":"Sun Zhengyu","year":"2024","unstructured":"Zhengyu Sun, Weiwei Sun, Shaohan Li, Zening Yang, Mutian Zhang, Yang Yang, Huayun Geng, and Jin Yu. 2024. CrysGraphFormer: An equivariant graph transformer for prediction of lattice thermal conductivity with interpretability. Journal of Materials Chemistry A 12, 44 (2024), 30707\u201330721.","journal-title":"Journal of Materials Chemistry A"},{"key":"e_1_3_1_142_2","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.1145\/3583780.3615061","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","author":"Tang Wenzhuo","year":"2023","unstructured":"Wenzhuo Tang, Hongzhi Wen, Renming Liu, Jiayuan Ding, Wei Jin, Yuying Xie, Hui Liu, and Jiliang Tang. 2023. Single-cell multimodal prediction via transformers. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 2422\u20132431."},{"key":"e_1_3_1_143_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Th\u00f6lke Philipp","year":"2022","unstructured":"Philipp Th\u00f6lke and Gianni De Fabritiis. 2022. Equivariant transformers for neural network based molecular potentials. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_144_2","doi-asserted-by":"crossref","first-page":"107982","DOI":"10.1016\/j.compbiolchem.2023.107982","article-title":"GTAMP-DTA: Graph transformer combined with attention mechanism for drug-target binding affinity prediction","volume":"108","author":"Tian Chuangchuang","year":"2024","unstructured":"Chuangchuang Tian, Luping Wang, Zhiming Cui, and Hongjie Wu. 2024. GTAMP-DTA: Graph transformer combined with attention mechanism for drug-target binding affinity prediction. Computational Biology and Chemistry 108 (2024), 107982.","journal-title":"Computational Biology and Chemistry"},{"key":"e_1_3_1_145_2","first-page":"5998","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the International Conference on Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_1_146_2","volume-title":"Proceedings of the ICLR 2022 Workshop on Geometrical and Topological Representation Learning","author":"Velickovic Petar","year":"2022","unstructured":"Petar Velickovic. 2022. Message passing all the way up. In Proceedings of the ICLR 2022 Workshop on Geometrical and Topological Representation Learning."},{"key":"e_1_3_1_147_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Velivckovic Petar","year":"2018","unstructured":"Petar Velivckovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_148_2","first-page":"4601","volume-title":"Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA)","author":"Vemula Anirudh","year":"2018","unstructured":"Anirudh Vemula, Katharina Muelling, and Jean Oh. 2018. Social attention: Modeling attention in human crowds. In Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 4601\u20134607."},{"key":"e_1_3_1_149_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Vignac Clement","year":"2023","unstructured":"Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan Cevher, and Pascal Frossard. 2023. DiGress: Discrete denoising diffusion for graph generation. In Proceedings of the 11th International Conference on Learning Representations."},{"issue":"8","key":"e_1_3_1_150_2","doi-asserted-by":"crossref","first-page":"2854","DOI":"10.1109\/TMI.2024.3381239","article-title":"Breast cancer classification from digital pathology images via connectivity-aware graph transformer","volume":"43","author":"Wang Kang","year":"2024","unstructured":"Kang Wang, Feiyang Zheng, Lan Cheng, Hong-Ning Dai, Qi Dou, and Jing Qin. 2024. Breast cancer classification from digital pathology images via connectivity-aware graph transformer. IEEE Transactions on Medical Imaging 43, 8 (2024), 2854\u20132865.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_3_1_151_2","volume-title":"Proceedings of the 13th International Conference on Learning Representations","author":"Wang Liang","year":"2025","unstructured":"Liang Wang, Shaozhen Liu, Yu Rong, Deli Zhao, Qiang Liu, Shu Wu, and Liang Wang. 2025. MolSpectra: Pre-training 3D molecular representation with multi-modal energy spectra. In Proceedings of the 13th International Conference on Learning Representations."},{"issue":"4","key":"e_1_3_1_152_2","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1109\/TKDE.2025.3533610","article-title":"HPST-GT: Full-link delivery time estimation via heterogeneous periodic spatial-temporal graph transformer","volume":"37","author":"Wang Shuai","year":"2025","unstructured":"Shuai Wang, Hai Wang, Li Lin, Xiaohui Zhao, Tian He, Dian Shen, and Wei Xi. 2025. HPST-GT: Full-link delivery time estimation via heterogeneous periodic spatial-temporal graph transformer. IEEE Transactions on Knowledge and Data Engineering 37, 4 (2025), 1885\u20131901.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_153_2","first-page":"283","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Wang Yingheng","year":"2024","unstructured":"Yingheng Wang, Shufeng Kong, John M. Gregoire, and Carla P. Gomes. 2024. Conformal crystal graph transformer with robust encoding of periodic invariance. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 283\u2013291."},{"issue":"1","key":"e_1_3_1_154_2","doi-asserted-by":"crossref","first-page":"bbad400","DOI":"10.1093\/bib\/bbad400","article-title":"BatmanNet: Bi-branch masked graph transformer autoencoder for molecular representation","volume":"25","author":"Wang Zhen","year":"2024","unstructured":"Zhen Wang, Zheng Feng, Yanjun Li, Bowen Li, Yongrui Wang, Chulin Sha, Min He, and Xiaolin Li. 2024. BatmanNet: Bi-branch masked graph transformer autoencoder for molecular representation. Briefings in Bioinformatics 25, 1 (2024), bbad400.","journal-title":"Briefings in Bioinformatics"},{"key":"e_1_3_1_155_2","doi-asserted-by":"crossref","first-page":"1055348","DOI":"10.3389\/frma.2022.1055348","article-title":"DGTR: Dynamic graph transformer for rumor detection","volume":"7","author":"Wei Siqi","year":"2023","unstructured":"Siqi Wei, Bin Wu, Aoxue Xiang, Yangfu Zhu, and Chenguang Song. 2023. DGTR: Dynamic graph transformer for rumor detection. Frontiers in Research Metrics and Analytics 7 (2023), 1055348.","journal-title":"Frontiers in Research Metrics and Analytics"},{"key":"e_1_3_1_156_2","first-page":"1508","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Wei Yinwei","year":"2023","unstructured":"Yinwei Wei, Wenqi Liu, Fan Liu, Xiang Wang, Liqiang Nie, and Tat-Seng Chua. 2023. LightGT: A light graph transformer for multimedia recommendation. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1508\u20131517."},{"key":"e_1_3_1_157_2","unstructured":"Hongzhi Wen Wenzhuo Tang Wei Jin Jiayuan Ding Renming Liu Feng Shi Yuying Xie and Jiliang Tang. 2023. Single cells are spatial tokens: Transformers for spatial transcriptomic data imputation. arXiv preprint arXiv:2302.03038. Retrieved from https:\/\/arxiv.org\/abs\/2302.03038"},{"key":"e_1_3_1_158_2","first-page":"6778","volume-title":"Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI-23","author":"Wen Qingsong","year":"2023","unstructured":"Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. 2023. Transformers in time series: A survey. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI-23. 6778\u20136786. Survey Track."},{"key":"e_1_3_1_159_2","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1016\/j.neunet.2023.11.018","article-title":"AttentionMGT-DTA: A multi-modal drug-target affinity prediction using graph transformer and attention mechanism","volume":"169","author":"Wu Hongjie","year":"2024","unstructured":"Hongjie Wu, Junkai Liu, Tengsheng Jiang, Quan Zou, Shujie Qi, Zhiming Cui, Prayag Tiwari, and Yijie Ding. 2024. AttentionMGT-DTA: A multi-modal drug-target affinity prediction using graph transformer and attention mechanism. Neural Networks 169 (2024), 623\u2013636.","journal-title":"Neural Networks"},{"key":"e_1_3_1_160_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Wu Huaijin","year":"2024","unstructured":"Huaijin Wu, Wei Liu, Yatao Bian, Jiaxiang Wu, Nianzu Yang, and Junchi Yan. 2024. EBMDock: Neural probabilistic protein-protein docking via a differentiable energy model. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_161_2","first-page":"27387","article-title":"Nodeformer: A scalable graph structure learning transformer for node classification","volume":"35","author":"Wu Qitian","year":"2022","unstructured":"Qitian Wu, Wentao Zhao, Zenan Li, David P. Wipf, and Junchi Yan. 2022. Nodeformer: A scalable graph structure learning transformer for node classification. Advances in Neural Information Processing Systems 35 (2022), 27387\u201327401.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_162_2","first-page":"64753","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","volume":"36","author":"Wu Qitian","year":"2023","unstructured":"Qitian Wu, Wentao Zhao, Chenxiao Yang, Hengrui Zhang, Fan Nie, Haitian Jiang, Yatao Bian, and Junchi Yan. 2023. SGFormer: Simplifying and empowering transformers for large-graph representations. In Proceedings of the International Conference on Neural Information Processing Systems 36 (2023), 64753\u201364773."},{"key":"e_1_3_1_163_2","first-page":"64753","article-title":"Simplifying and empowering transformers for large-graph representations","volume":"36","author":"Wu Qitian","year":"2024","unstructured":"Qitian Wu, Wentao Zhao, Chenxiao Yang, Hengrui Zhang, Fan Nie, Haitian Jiang, Yatao Bian, and Junchi Yan. 2024. Simplifying and empowering transformers for large-graph representations. Advances in Neural Information Processing Systems 36 (2024), 64753\u201364773.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"e_1_3_1_164_2","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1007\/s13278-024-01263-4","article-title":"Lgt: Long-range graph transformer for early rumor detection","volume":"14","author":"Xia Jinghong","year":"2024","unstructured":"Jinghong Xia, Yuling Li, and Kui Yu. 2024. Lgt: Long-range graph transformer for early rumor detection. Social Network Analysis and Mining 14, 1 (2024), 100.","journal-title":"Social Network Analysis and Mining"},{"key":"e_1_3_1_165_2","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Xing Yujie","year":"2024","unstructured":"Yujie Xing, Xiao Wang, Yibo Li, Hai Huang, and Chuan Shi. 2024. Less is more: On the over-globalizing problem in graph transformers. In Proceedings of the 41st International Conference on Machine Learning."},{"key":"e_1_3_1_166_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Xu Guikun","year":"2024","unstructured":"Guikun Xu, Yongquan Jiang, PengChuan Lei, Yan Yang, and Jim Chen. 2024. GTMGC: Using graph transformer to predict molecule\u2019s ground-state conformation. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_167_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks?. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_168_2","first-page":"5453","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In Proceedings of the International Conference on Machine Learning. PMLR, 5453\u20135462."},{"key":"e_1_3_1_169_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Yan Keqiang","year":"2024","unstructured":"Keqiang Yan, Cong Fu, Xiaofeng Qian, Xiaoning Qian, and Shuiwang Ji. 2024. Complete and efficient graph transformers for crystal material property prediction. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_170_2","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Yan Keqiang","year":"2022","unstructured":"Keqiang Yan, Yi Liu, Yuchao Lin, and Shuiwang Ji. 2022. Periodic graph transformers for crystal material property prediction. In Proceedings of the International Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_171_2","unstructured":"Han Yang Chenxi Hu Yichi Zhou Xixian Liu Yu Shi Jielan Li Guanzhi Li Zekun Chen Shuizhou Chen Claudio Zeni et\u00a0al. 2024. MatterSim: A deep learning atomistic model across elements temperatures and pressures. arXiv preprint arXiv:2405.04967. Retrieved from https:\/\/arxiv.org\/abs\/2405.04967"},{"key":"e_1_3_1_172_2","first-page":"28798","article-title":"GraphFormers: GNN-nested transformers for representation learning on textual graph","volume":"34","author":"Yang Junhan","year":"2021","unstructured":"Junhan Yang, Zheng Liu, Shitao Xiao, Chaozhuo Li, Defu Lian, Sanjay Agrawal, Amit Singh, Guangzhong Sun, and Xing Xie. 2021. GraphFormers: GNN-nested transformers for representation learning on textual graph. Advances in Neural Information Processing Systems 34 (2021), 28798\u201328810.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_173_2","first-page":"7145","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Yao Shaowei","year":"2020","unstructured":"Shaowei Yao, Tianming Wang, and Xiaojun Wan. 2020. Heterogeneous graph transformer for graph-to-sequence learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, 7145\u20137154."},{"key":"e_1_3_1_174_2","first-page":"28877","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation?. In Proceedings of the International Conference on Neural Information Processing Systems. 28877\u201328888."},{"key":"e_1_3_1_175_2","first-page":"507","volume-title":"ECCV 2020: Proceedings of the 16th European Conference on Computer Vision, Part XII 16","author":"Yu Cunjun","year":"2020","unstructured":"Cunjun Yu, Xiao Ma, Jiawei Ren, Haiyu Zhao, and Shuai Yi. 2020. Spatio-temporal graph transformer networks for pedestrian trajectory prediction. In ECCV 2020: Proceedings of the 16th European Conference on Computer Vision, Part XII 16. Springer, 507\u2013523."},{"key":"e_1_3_1_176_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Yu Qiying","year":"2024","unstructured":"Qiying Yu, Yudi Zhang, Yuyan Ni, Shikun Feng, Yanyan Lan, Hao Zhou, and Jingjing Liu. 2024. Multimodal molecular pretraining via modality blending. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_1_177_2","volume-title":"Proceedings of the 38th Annual Conference on Neural Information Processing Systems","author":"Yu Shuo","year":"2024","unstructured":"Shuo Yu, Shan Jin, Ming Li, Tabinda Sarwar, and Feng Xia. 2024. Long-range Brain Graph Transformer. In Proceedings of the 38th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_178_2","doi-asserted-by":"crossref","first-page":"1855","DOI":"10.1145\/3690624.3709199","volume-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1","author":"Yuan Chaohao","year":"2025","unstructured":"Chaohao Yuan, Songyou Li, Geyan Ye, Yikun Zhang, Long-Kai Huang, Wenbing Huang, Wei Liu, Jianhua Yao, and Yu Rong. 2025. Annotation-guided protein design with multi-level domain alignment. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1. 1855\u20131866."},{"key":"e_1_3_1_179_2","first-page":"881","volume-title":"Proceedings of the 19th ACM International Conference on Web Search and Data Mining","author":"Yuan Chaohao","year":"2026","unstructured":"Chaohao Yuan, Zhenjie Song, Ercan Engin Kuruoglu, Kangfei Zhao, Yang Liu, Deli Zhao, Hong Cheng, and Yu Rong. 2026. ParaFormer: A generalized pagerank graph transformer for graph representation learning. In Proceedings of the 19th ACM International Conference on Web Search and Data Mining. 881\u2013891."},{"issue":"2","key":"e_1_3_1_180_2","doi-asserted-by":"crossref","first-page":"bbab564","DOI":"10.1093\/bib\/bbab564","article-title":"AlphaFold2-Aware protein\u2013DNA binding site prediction using graph transformer","volume":"23","author":"Yuan Qianmu","year":"2022","unstructured":"Qianmu Yuan, Sheng Chen, Jiahua Rao, Shuangjia Zheng, Huiying Zhao, and Yuedong Yang. 2022. AlphaFold2-Aware protein\u2013DNA binding site prediction using graph transformer. Briefings in Bioinformatics 23, 2 (2022), bbab564.","journal-title":"Briefings in Bioinformatics"},{"key":"e_1_3_1_181_2","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume":"33","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, et\u00a0al. 2020. Big bird: Transformers for longer sequences. Advances in Neural Information Processing Systems 33 (2020), 17283\u201317297.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_182_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Zaidi Sheheryar","year":"2023","unstructured":"Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter Battaglia, Razvan Pascanu, and Jonathan Godwin. 2023. Pre-training via denoising for molecular property prediction. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_183_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Zhang Bohang","year":"2023","unstructured":"Bohang Zhang, Shengjie Luo, Liwei Wang, and Di He. 2023. Rethinking the expressive power of GNNs via graph biconnectivity. In Proceedings of the 11th International Conference on Learning Representations."},{"issue":"1","key":"e_1_3_1_184_2","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1038\/s41524-024-01493-2","article-title":"DPA-2: A large atomic model as a multi-task learner","volume":"10","author":"Zhang Duo","year":"2024","unstructured":"Duo Zhang, Xinzijian Liu, Xiangyu Zhang, Chengqian Zhang, Chun Cai, Hangrui Bi, Yiming Du, Xuejian Qin, Anyang Peng, Jiameng Huang, et\u00a0al. 2024. DPA-2: A large atomic model as a multi-task learner. npj Computational Materials 10, 1 (2024), 293.","journal-title":"npj Computational Materials"},{"key":"e_1_3_1_185_2","volume-title":"Proceedings of the 39th Annual Conference on Neural Information Processing Systems","author":"Zhang Geng","year":"2026","unstructured":"Geng Zhang, Jiangrong Shen, Kaizhong Zheng, Liangjun Chen, and Badong Chen. 2026. Local-global coupling spiking graph transformer for brain disorders diagnosis from two perspectives. In Proceedings of the 39th Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_1_186_2","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Zhang Haopeng","year":"2020","unstructured":"Haopeng Zhang and Jiawei Zhang. 2020. Text graph transformer for document classification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_1_187_2","unstructured":"Jiawei Zhang Haopeng Zhang Congying Xia and Li Sun. 2020. Graph-bert: Only attention is needed for learning graph representations. arXiv preprint arXiv:2001.05140. Retrieved from https:\/\/arxiv.org\/abs\/2001.05140"},{"key":"e_1_3_1_188_2","first-page":"7205","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Zhang Lijun","year":"2024","unstructured":"Lijun Zhang, Kangkang Zhou, Feng Lu, Xiang-Dong Zhou, and Yu Shi. 2024. Deep semantic graph transformer for multi-view 3D human pose estimation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 7205\u20137214."},{"key":"e_1_3_1_189_2","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1145\/3626772.3657721","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Zhang Peiyan","year":"2024","unstructured":"Peiyan Zhang, Yuchen Yan, Xi Zhang, Chaozhuo Li, Senzhang Wang, Feiran Huang, and Sunghun Kim. 2024. TransGNN: Harnessing the collaborative power of transformers and graph neural networks for recommender systems. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1285\u20131295."},{"key":"e_1_3_1_190_2","first-page":"374","volume-title":"Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Zhang Xuan","year":"2022","unstructured":"Xuan Zhang, Cheng Chen, Zhaoxu Meng, Zhenghe Yang, Haitao Jiang, and Xuefeng Cui. 2022. CoAtGIN: Marrying convolution and attention for graph-based molecule property prediction. In Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 374\u2013379."},{"key":"e_1_3_1_191_2","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1145\/3589334.3645680","volume-title":"Proceedings of the ACM Web Conference 2024","author":"Zhang Yuchen","year":"2024","unstructured":"Yuchen Zhang, Xiaoxiao Ma, Jia Wu, Jian Yang, and Hao Fan. 2024. Heterogeneous subgraph transformer for fake news detection. In Proceedings of the ACM Web Conference 2024. 1272\u20131282."},{"key":"e_1_3_1_192_2","doi-asserted-by":"crossref","first-page":"21171","DOI":"10.52202\/068431-1539","article-title":"Hierarchical graph transformer with adaptive node sampling","volume":"35","author":"Zhang Zaixi","year":"2022","unstructured":"Zaixi Zhang, Qi Liu, Qingyong Hu, and Chee-Kong Lee. 2022. Hierarchical graph transformer with adaptive node sampling. Advances in Neural Information Processing Systems 35 (2022), 21171\u201321183.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_193_2","volume-title":"Proceedings of the 37th Conference on Neural Information Processing Systems","author":"Zhang Zaixi","year":"2023","unstructured":"Zaixi Zhang, Zepu Lu, Zhongkai Hao, Marinka Zitnik, and Qi Liu. 2023. Full-atom protein pocket design via iterative refinement. In Proceedings of the 37th Conference on Neural Information Processing Systems."},{"issue":"11","key":"e_1_3_1_194_2","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1038\/s42256-024-00920-9","article-title":"Efficient generation of protein pockets with PocketGen","volume":"6","author":"Zhang Zaixi","year":"2024","unstructured":"Zaixi Zhang, Wan Xiang Shen, Qi Liu, and Marinka Zitnik. 2024. Efficient generation of protein pockets with PocketGen. Nature Machine Intelligence 6, 11 (2024), 1382\u20131395.","journal-title":"Nature Machine Intelligence"},{"key":"e_1_3_1_195_2","doi-asserted-by":"crossref","first-page":"3412","DOI":"10.1145\/3583780.3614893","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","author":"Zhao Kangfei","year":"2023","unstructured":"Kangfei Zhao, Yu Rong, Biaobin Jiang, Jianheng Tang, Hengtong Zhang, Jeffrey Xu Yu, and Peilin Zhao. 2023. Geometric graph learning for protein mutation effect prediction. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 3412\u20133422."},{"key":"e_1_3_1_196_2","first-page":"3606","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Zhao Weiqin","year":"2023","unstructured":"Weiqin Zhao, Shujun Wang, Maximus Yeung, Tianye Niu, and Lequan Yu. 2023. MulGT: Multi-task graph-transformer with task-aware knowledge injection and domain knowledge-driven pooling for whole slide image analysis. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 3606\u20133614."},{"key":"e_1_3_1_197_2","first-page":"20438","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhao Weixi","year":"2022","unstructured":"Weixi Zhao, Weiqiang Wang, and Yunjie Tian. 2022. GraFormer: Graph-oriented transformer for 3D pose estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20438\u201320447."},{"key":"e_1_3_1_198_2","doi-asserted-by":"crossref","first-page":"3402","DOI":"10.1145\/3583780.3614918","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","author":"Zhao Xiaohui","year":"2023","unstructured":"Xiaohui Zhao, Shuai Wang, Hai Wang, Tian He, Desheng Zhang, and Guang Wang. 2023. HST-GT: Heterogeneous spatial-temporal graph transformer for delivery time estimation in warehouse-distribution integration e-commerce. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 3402\u20133411."},{"key":"e_1_3_1_199_2","first-page":"1234","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Zheng Chuanpan","year":"2020","unstructured":"Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, and Jianzhong Qi. 2020. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 1234\u20131241."},{"key":"e_1_3_1_200_2","doi-asserted-by":"crossref","first-page":"5496","DOI":"10.1145\/3503161.3547844","volume-title":"Proceedings of the 30th ACM International Conference on Multimedia","author":"Zheng Ce","year":"2022","unstructured":"Ce Zheng, Matias Mendieta, Pu Wang, Aidong Lu, and Chen Chen. 2022. A lightweight graph transformer network for human mesh reconstruction from 2D human pose. In Proceedings of the 30th ACM International Conference on Multimedia. 5496\u20135507."},{"key":"e_1_3_1_201_2","first-page":"70","volume-title":"Proceedings of the 2024 IEEE 40th International Conference on Data Engineering (ICDE)","author":"Zheng Juncheng","year":"2024","unstructured":"Juncheng Zheng, Meiyu Liang, Yang Yu, Yawen Li, and Zhe Xue. 2024. Knowledge graph enhanced multimodal transformer for image-text retrieval. In Proceedings of the 2024 IEEE 40th International Conference on Data Engineering (ICDE). IEEE, 70\u201382."},{"issue":"11","key":"e_1_3_1_202_2","doi-asserted-by":"crossref","first-page":"3003","DOI":"10.1109\/TMI.2022.3176598","article-title":"A graph-transformer for whole slide image classification","volume":"41","author":"Zheng Yi","year":"2022","unstructured":"Yi Zheng, Rushin H. Gindra, Emily J. Green, Eric J. Burks, Margrit Betke, Jennifer E. Beane, and Vijaya B. Kolachalama. 2022. A graph-transformer for whole slide image classification. IEEE Transactions on Medical Imaging 41, 11 (2022), 3003\u20133015.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"e_1_3_1_203_2","first-page":"42317","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zheng Zaixiang","year":"2023","unstructured":"Zaixiang Zheng, Yifan Deng, Dongyu Xue, Yi Zhou, Fei Ye, and Quanquan Gu. 2023. Structure-informed language models are protein designers. In Proceedings of the International Conference on Machine Learning. PMLR, 42317\u201342338."},{"key":"e_1_3_1_204_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Zhou Gengmo","year":"2023","unstructured":"Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. 2023. Uni-Mol: A universal 3D molecular representation learning framework. In Proceedings of the 11th International Conference on Learning Representations."},{"issue":"1","key":"e_1_3_1_205_2","doi-asserted-by":"crossref","first-page":"7434","DOI":"10.1038\/s41467-023-43166-6","article-title":"ProRefiner: An entropy-based refining strategy for inverse protein folding with global graph attention","volume":"14","author":"Zhou Xinyi","year":"2023","unstructured":"Xinyi Zhou, Guangyong Chen, Junjie Ye, Ercheng Wang, Jun Zhang, Cong Mao, Zhanwei Li, Jianye Hao, Xingxu Huang, Jin Tang, et\u00a0al. 2023. ProRefiner: An entropy-based refining strategy for inverse protein folding with global graph attention. Nature Communications 14, 1 (2023), 7434.","journal-title":"Nature Communications"},{"key":"e_1_3_1_206_2","first-page":"679","volume-title":"Proceedings of the 16th ACM International Conference on Web Search and Data Mining","author":"Zhou Xin","year":"2023","unstructured":"Xin Zhou, Jinglong Wang, Yong Liu, Xingyu Wu, Zhiqi Shen, and Cyril Leung. 2023. Inductive graph transformer for delivery time estimation. In Proceedings of the 16th ACM International Conference on Web Search and Data Mining. 679\u2013687."},{"key":"e_1_3_1_207_2","first-page":"4652","volume-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Zhu Junyou","year":"2024","unstructured":"Junyou Zhu, Chao Gao, Ze Yin, Xianghua Li, and J\u00fcrgen Kurths. 2024. Propagation structure-aware graph transformer for robust and interpretable fake news detection. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4652\u20134663."},{"key":"e_1_3_1_208_2","first-page":"5459","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Zhu Jie","year":"2019","unstructured":"Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, and Guodong Zhou. 2019. Modeling graph structure in transformer for better AMR-to-text generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, 5459\u20135468."},{"key":"e_1_3_1_209_2","first-page":"3615","volume-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Zhu Jinhua","year":"2023","unstructured":"Jinhua Zhu, Yingce Xia, Lijun Wu, Shufang Xie, Wengang Zhou, Tao Qin, Houqiang Li, and Tie-Yan Liu. 2023. Dual-view molecular pre-training. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 3615\u20133627."},{"key":"e_1_3_1_210_2","first-page":"1359","volume-title":"Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI-21","author":"Zhu Yiran","year":"2021","unstructured":"Yiran Zhu, Xing Xu, Fumin Shen, Yanli Ji, Lianli Gao, and Heng Tao Shen. 2021. PoseGTAC: Graph transformer encoder-decoder with atrous convolution for 3D human pose estimation. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI-21. 1359\u20131365."},{"key":"e_1_3_1_211_2","volume-title":"Proceedings of the 13th International Conference on Learning Representations","author":"Zhuo Jiaming","year":"2025","unstructured":"Jiaming Zhuo, Yuwei Liu, Yintong Lu, Ziyi Ma, Kun Fu, Chuan Wang, Yuanfang Guo, Zhen Wang, Xiaochun Cao, and Liang Yang. 2025. DUALFormer: Dual graph transformer. In Proceedings of the 13th International Conference on Learning Representations."}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3834764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T15:21:49Z","timestamp":1787412109000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3834764"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":210,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2026,11,30]]}},"alternative-id":["10.1145\/3834764"],"URL":"https:\/\/doi.org\/10.1145\/3834764","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,22]]},"assertion":[{"value":"2025-06-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}