{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T19:04:26Z","timestamp":1776279866295,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583493","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"599-610","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":67,"title":["HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7259-1087","authenticated-orcid":false,"given":"Qiheng","family":"Mao","sequence":"first","affiliation":[{"name":"Zhejiang University, China and Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6262-9435","authenticated-orcid":false,"given":"Zemin","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6934-2354","authenticated-orcid":false,"given":"Chenghao","family":"Liu","sequence":"additional","affiliation":[{"name":"Salesforce Research Asia, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-6020","authenticated-orcid":false,"given":"Jianling","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205","author":"Alon Uri","year":"2020","unstructured":"Uri Alon and Eran Yahav. 2020. On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Layer normalization. arXiv preprint arXiv:1607.06450","author":"Ba Jimmy\u00a0Lei","year":"2016","unstructured":"Jimmy\u00a0Lei Ba, Jamie\u00a0Ryan Kiros, and Geoffrey\u00a0E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_1_4_1","volume-title":"How attentive are graph attention networks?arXiv preprint arXiv:2105.14491","author":"Brody Shaked","year":"2021","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2021. How attentive are graph attention networks?arXiv preprint arXiv:2105.14491 (2021)."},{"key":"e_1_3_2_1_5_1","first-page":"1616","article-title":"A comprehensive survey of graph embedding: Problems, techniques, and applications","volume":"30","author":"Cai Hongyun","year":"2018","unstructured":"Hongyun Cai, Vincent\u00a0W Zheng, and Kevin Chen-Chuan Chang. 2018. A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE TKDE 30, 9 (2018), 1616\u20131637.","journal-title":"IEEE TKDE"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning. PMLR, 3469\u20133489","author":"Chen Dexiong","year":"2022","unstructured":"Dexiong Chen, Leslie O\u2019Bray, and Karsten Borgwardt. 2022. Structure-aware transformer for graph representation learning. In International Conference on Machine Learning. PMLR, 3469\u20133489."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_3_2_1_9_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699","author":"Dwivedi Vijay\u00a0Prakash","year":"2020","unstructured":"Vijay\u00a0Prakash Dwivedi and Xavier Bresson. 2020. A generalization of transformer networks to graphs. arXiv preprint arXiv:2012.09699 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 1797\u20131806","author":"Lee Wang-Chien","year":"2017","unstructured":"Tao-yang Fu, Wang-Chien Lee, and Zhen Lei. 2017. Hin2vec: Explore meta-paths in heterogeneous information networks for representation learning. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 1797\u20131806."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In KDD. 855\u2013864.","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_2_1_14_1","unstructured":"William\u00a0L Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS. 1025\u20131035."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5833"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939815"},{"key":"e_1_3_2_1_20_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2015","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_21_1","unstructured":"Thomas\u00a0N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR."},{"key":"e_1_3_2_1_22_1","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 L\u00e9tourneau, 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_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.08.028"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/210"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467276"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10486"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1150\u20131160","author":"Lv Qingsong","year":"2021","unstructured":"Qingsong Lv, Ming Ding, Qiang Liu, Yuxiang Chen, Wenzheng Feng, Siming He, Chang Zhou, Jianguo Jiang, Yuxiao Dong, and Jie Tang. 2021. Are we really making much progress? Revisiting, benchmarking and refining heterogeneous graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1150\u20131160."},{"key":"e_1_3_2_1_29_1","volume-title":"Graphit: Encoding graph structure in transformers. arXiv preprint arXiv:2106.05667","author":"Mialon Gr\u00e9goire","year":"2021","unstructured":"Gr\u00e9goire Mialon, Dexiong Chen, Margot Selosse, and Julien Mairal. 2021. Graphit: Encoding graph structure in transformers. arXiv preprint arXiv:2106.05667 (2021)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Bryan Perozzi Rami Al-Rfou and Steven Skiena. 2014. DeepWalk: Online learning of social representations. In KDD. 701\u2013710.","DOI":"10.1145\/2623330.2623732"},{"key":"e_1_3_2_1_31_1","volume-title":"Powerful, Scalable Graph Transformer. arXiv preprint arXiv:2205.12454","author":"Ramp\u00e1\u0161ek Ladislav","year":"2022","unstructured":"Ladislav Ramp\u00e1\u0161ek, Mikhail Galkin, Vijay\u00a0Prakash Dwivedi, Anh\u00a0Tuan Luu, Guy Wolf, and Dominique Beaini. 2022. Recipe for a General, Powerful, Scalable Graph Transformer. arXiv preprint arXiv:2205.12454 (2022)."},{"key":"e_1_3_2_1_32_1","volume-title":"L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507","author":"Ranjan Rajeev","year":"2017","unstructured":"Rajeev Ranjan, Carlos\u00a0D Castillo, and Rama Chellappa. 2017. L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Dropedge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903","author":"Rong Yu","year":"2019","unstructured":"Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2019. Dropedge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903 (2019)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00056"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-022-01694-5"},{"key":"e_1_3_2_1_36_1","volume-title":"Ivan Titov, and Max Welling.","author":"Schlichtkrull Michael","year":"2018","unstructured":"Michael Schlichtkrull, Thomas\u00a0N Kipf, Peter Bloem, Rianne van\u00a0den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European semantic web conference. Springer, 593\u2013607."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2598561"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220006"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/2371211"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402736"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783307"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Jie Tang Jing Zhang Limin Yao Juanzi Li Li Zhang and Zhong Su. 2008. ArnetMiner: Extraction and Mining of Academic Social Networks. In KDD\u201908. 990\u2013998.","DOI":"10.1145\/1401890.1402008"},{"key":"e_1_3_2_1_44_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_45_1","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2018. Graph attention networks. In ICLR."},{"key":"e_1_3_2_1_46_1","volume-title":"A survey on heterogeneous graph embedding: methods, techniques, applications and sources","author":"Wang Xiao","year":"2022","unstructured":"Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye, and S\u00a0Yu Philip. 2022. A survey on heterogeneous graph embedding: methods, techniques, applications and sources. IEEE Transactions on Big Data (2022)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Xiao Wang Houye Ji Chuan Shi Bai Wang Yanfang Ye Peng Cui and Philip\u00a0S Yu. 2019. Heterogeneous graph attention network. In The world wide web conference. 2022\u20132032.","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467415"},{"key":"e_1_3_2_1_49_1","first-page":"13266","article-title":"Representing long-range context for graph neural networks with global attention","volume":"34","author":"Wu Zhanghao","year":"2021","unstructured":"Zhanghao Wu, Paras Jain, Matthew Wright, Azalia Mirhoseini, Joseph\u00a0E Gonzalez, and Ion Stoica. 2021. Representing long-range context for graph neural networks with global attention. Advances in Neural Information Processing Systems 34 (2021), 13266\u201313279.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","first-page":"4","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu Zonghan","year":"2020","unstructured":"Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S\u00a0Yu Philip. 2020. A comprehensive survey on graph neural networks. IEEE TNNLS 32, 1 (2020), 4\u201324.","journal-title":"IEEE TNNLS"},{"key":"e_1_3_2_1_51_1","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2019. How powerful are graph neural networks?. In ICLR."},{"key":"e_1_3_2_1_52_1","volume-title":"Heterogeneous network representation learning: A unified framework with survey and benchmark","author":"Yang Carl","year":"2020","unstructured":"Carl Yang, Yuxin Xiao, Yu Zhang, Yizhou Sun, and Jiawei Han. 2020. Heterogeneous network representation learning: A unified framework with survey and benchmark. IEEE Transactions on Knowledge and Data Engineering (2020)."},{"key":"e_1_3_2_1_53_1","volume-title":"Do transformers really perform badly for graph representation?Advances in Neural Information Processing Systems 34","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?Advances in Neural Information Processing Systems 34 (2021), 28877\u201328888."},{"key":"e_1_3_2_1_54_1","volume-title":"Do transformers really perform badly for graph representation?Advances in Neural Information Processing Systems 34","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?Advances in Neural Information Processing Systems 34 (2021), 28877\u201328888."},{"key":"e_1_3_2_1_55_1","unstructured":"Zhitao Ying Jiaxuan You Christopher Morris Xiang Ren Will Hamilton and Jure Leskovec. 2018. Hierarchical Graph Representation Learning with Differentiable Pooling. In NeurIPS. 4800\u20134810."},{"key":"e_1_3_2_1_56_1","first-page":"17009","article-title":"Design space for graph neural networks","volume":"33","author":"You Jiaxuan","year":"2020","unstructured":"Jiaxuan You, Zhitao Ying, and Jure Leskovec. 2020. Design space for graph neural networks. Advances in Neural Information Processing Systems 33 (2020), 17009\u201317021.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_57_1","volume-title":"Graph transformer networks. Advances in neural information processing systems 32","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo\u00a0J Kim. 2019. Graph transformer networks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"e_1_3_2_1_59_1","volume-title":"Gophormer: Ego-Graph Transformer for Node Classification. arXiv preprint arXiv:2110.13094","author":"Zhao Jianan","year":"2021","unstructured":"Jianan Zhao, Chaozhuo Li, Qianlong Wen, Yiqi Wang, Yuming Liu, Hao Sun, Xing Xie, and Yanfang Ye. 2021. Gophormer: Ego-Graph Transformer for Node Classification. arXiv preprint arXiv:2110.13094 (2021)."},{"key":"e_1_3_2_1_60_1","volume-title":"Pairnorm: Tackling oversmoothing in gnns. arXiv preprint arXiv:1909.12223","author":"Zhao Lingxiao","year":"2019","unstructured":"Lingxiao Zhao and Leman Akoglu. 2019. Pairnorm: Tackling oversmoothing in gnns. arXiv preprint arXiv:1909.12223 (2019)."},{"key":"e_1_3_2_1_61_1","volume-title":"A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network. arXiv preprint arXiv:2202.09177","author":"Zhao Tianyu","year":"2022","unstructured":"Tianyu Zhao, Cheng Yang, Yibo Li, Quan Gan, Zhenyi Wang, Fengqi Liang, Huan Zhao, Yingxia Shao, Xiao Wang, and Chuan Shi. 2022. Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network. arXiv preprint arXiv:2202.09177 (2022)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00203"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583493","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:02Z","timestamp":1750178822000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583493"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":62,"alternative-id":["10.1145\/3543507.3583493","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583493","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}