{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T16:21:58Z","timestamp":1772986918855,"version":"3.50.1"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"crossref","award":["62506155"],"award-info":[{"award-number":["62506155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Provincial Natural Science Fund of Jiangsu","award":["BK20251985"],"award-info":[{"award-number":["BK20251985"]}]},{"name":"Suzhou Municipal Leading Talents Fund","award":["2025"],"award-info":[{"award-number":["2025"]}]},{"DOI":"10.13039\/501100001809","name":"NSF of China","doi-asserted-by":"crossref","award":["62336003, 12371510"],"award-info":[{"award-number":["62336003, 12371510"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NSFC General Program","award":["62376235"],"award-info":[{"award-number":["62376235"]}]},{"name":"RGC General Research Fund","award":["12200725"],"award-info":[{"award-number":["12200725"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Recently, Graph Transformer (GT) models have been widely used in the task of Molecular Property Prediction (MPP) due to their high reliability in characterizing the latent relationship among graph nodes (i.e., the atoms in a molecule). However, most existing GT-based methods usually explore the basic interactions between pairwise atoms, and thus they fail to consider the important interactions among critical motifs (e.g., functional groups consisted of several atoms) of molecules. As motifs in a molecule are significant patterns that are of great importance for determining molecular properties (e.g., toxicity and solubility), overlooking motif interactions inevitably hinders the effectiveness of MPP. To address this issue, we propose a novel Atom-Motif Contrastive Transformer (AMCT), which not only explores the atom-level interactions but also considers the motif-level interactions. Since the representations of atoms and motifs for a given molecule are actually two different views of the same instance, they are naturally aligned to generate the self-supervisory signals for model training. Meanwhile, the same motif can exist in different molecules, and hence we also employ the contrastive loss to maximize the representation agreement of identical motifs across different molecules. Finally, in order to clearly identify the motifs that are critical in deciding the properties of each molecule, we further construct a property-aware attention mechanism into our learning framework. Our proposed AMCT is extensively evaluated on 10 popular benchmark datasets, and both quantitative and qualitative results firmly demonstrate its effectiveness when compared with the state-of-the-art methods.<\/jats:p>","DOI":"10.1145\/3787204","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T10:06:38Z","timestamp":1768817198000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Atom-Motif Contrastive Transformer for Molecular Property Prediction"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1416-5255","authenticated-orcid":false,"given":"Wentao","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0159-8851","authenticated-orcid":false,"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University, Suzhou, China and RIKEN Center for Advanced Intelligence Project, Chuo-ku, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1154-6194","authenticated-orcid":false,"given":"Chen","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6338-0958","authenticated-orcid":false,"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China and RIKEN Center for Advanced Intelligence Project, Chuo-ku, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7353-5079","authenticated-orcid":false,"given":"Gang","family":"Niu","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Chuo-ku, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6658-6743","authenticated-orcid":false,"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"RIKEN Center for Advanced Intelligence Project, Chuo-ku, Japan and Complexity Science and Engineering, The University of Tokyo, Bunkyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Junyu Lin Yan Zheng Xinyue Chen Yazhou Ren Xiaorong Pu and Jing He. 2024. Cross-view contrastive unification guides generative pretraining for molecular property prediction. In Proceedings of the 32nd ACM International Conference on Multimedia 1\u20139.","DOI":"10.1145\/3664647.3681193"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448733"},{"key":"e_1_3_2_4_2","first-page":"28877","volume-title":"Proceedings of Advances in 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 Advances in Neural Information Processing Systems, 28877\u201328888."},{"key":"e_1_3_2_5_2","first-page":"14501","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Ramp\u00e1\u0161ek Ladislav","year":"2022","unstructured":"Ladislav Ramp\u00e1\u0161ek, Michael Galkin, Vijay Prakash Dwivedi, Anh Tuan Luu, Guy Wolf, and Dominique Beaini. 2022. Recipe for a general, powerful, scalable graph transformer. In Proceedings of Advances in Neural Information Processing Systems, 14501\u201314515."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25662"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00816-8"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.298.5594.824"},{"key":"e_1_3_2_9_2","first-page":"15870","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Zhang Zaixi","year":"2021","unstructured":"Zaixi Zhang, Qi Liu, Hao Wang, Chengqiang Lu, and Chee-Kong Lee. 2021. Motif-based graph self-supervised learning for molecular property prediction. In Proceedings of Advances in Neural Information Processing Systems, 15870\u201315882."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3364059"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1021\/ja2069592"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1109778"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1201\/9780203750841"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"e_1_3_2_15_2","first-page":"19620","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Luo Dongsheng","year":"2020","unstructured":"Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, and Xiang Zhang. 2020. Parameterized explainer for graph neural network. In Proceedings of Advances in Neural Information Processing Systems, 19620\u201319631."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00284-w"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29772"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579828"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.108"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3110813"},{"issue":"6","key":"e_1_3_2_21_2","first-page":"1687","article-title":"Advances of hyperspectral image classification based on graph neural networks","volume":"51","author":"Wan Sheng","year":"2023","unstructured":"Sheng Wan, Jian Yang, and Chen Gong. 2023. Advances of hyperspectral image classification based on graph neural networks. Acta Electronica Sinica 51, 6 (2023), 1687\u20131709.","journal-title":"Acta Electronica Sinica"},{"issue":"1","key":"e_1_3_2_22_2","first-page":"1","article-title":"Hyperspectral image classification with contrastive graph convolutional network","volume":"61","author":"Yu Wentao","year":"2023","unstructured":"Wentao Yu, Sheng Wan, Guangyu Li, Jian Yang, and Chen Gong. 2023. Hyperspectral image classification with contrastive graph convolutional network. IEEE Transactions on Geoscience and Remote Sensing 61, 1 (2023), 1\u201315.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM59182.2024.00071"},{"issue":"1","key":"e_1_3_2_24_2","first-page":"1","article-title":"FedTPS: Traffic pattern sharing for personalized federated traffic flow prediction","volume":"1","author":"Zhou Hang","year":"2025","unstructured":"Hang Zhou, Wentao Yu, Sheng Wan, Yongxin Tong, Tianlong Gu, and Chen Gong. 2025. FedTPS: Traffic pattern sharing for personalized federated traffic flow prediction. Knowledge and Information Systems 1, 1 (2025), 1\u201327.","journal-title":"Knowledge and Information Systems"},{"key":"e_1_3_2_25_2","first-page":"1","article-title":"Modeling inter-intra heterogeneity for graph federated learning","author":"Yu Wentao","year":"2025","unstructured":"Wentao Yu, Shuo Chen, Yongxin Tong, Tianlong Gu, and Chen Gong. 2025. Modeling inter-intra heterogeneity for graph federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence, 1\u20139.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_26_2","unstructured":"Wentao Yu. 2025. Homophily heterogeneity matters in graph federated learning: A spectrum sharing and complementing perspective. arXiv:2502.13732. Retrieved from https:\/\/arxiv.org\/abs\/2502.13732"},{"key":"e_1_3_2_27_2","unstructured":"Wentao Yu Chen Gong Bo Han Lixin Fan and Qiang Yang. 2025. Integrating commonality and individuality for graph federated learning: A graph spectrum perspective. Retrieved from https:\/\/www.techrxiv.org\/doi\/full\/10.36227\/techrxiv.175502607.78991557"},{"key":"e_1_3_2_28_2","first-page":"1","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of Advances in Neural Information Processing Systems, 1\u201311."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591361"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3653986"},{"key":"e_1_3_2_31_2","first-page":"1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence Workshop on Deep Learning on Graphs: Methods and Applications","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 Conference on Artificial Intelligence Workshop on Deep Learning on Graphs: Methods and Applications, 1\u20138."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3232117"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593590"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20313"},{"key":"e_1_3_2_35_2","first-page":"25581","volume-title":"Proceedings of International Conference on Machine Learning","author":"Yu Zhaoning","year":"2022","unstructured":"Zhaoning Yu and Hongyang Gao. 2022. Molecular representation learning via heterogeneous motif graph neural networks. In Proceedings of International Conference on Machine Learning, 25581\u201325594."},{"key":"e_1_3_2_36_2","first-page":"22118","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. In Proceedings of Advances in Neural Information Processing Systems, 22118\u201322133."},{"key":"e_1_3_2_37_2","unstructured":"Zhaoning Yu and Hongyang Gao. 2023. A data-driven approach for effective motif extraction and molecular representation learning. arXiv:2312.15387. Retrieved from https:\/\/arxiv.org\/abs\/2312.15387"},{"key":"e_1_3_2_38_2","first-page":"2323","volume-title":"Proceedings of International Conference on Machine Learning","author":"Jin Wengong","year":"2018","unstructured":"Wengong Jin, Regina Barzilay, and Tommi Jaakkola. 2018. Junction tree variational autoencoder for molecular graph generation. In Proceedings of International Conference on Machine Learning, 2323\u20132332."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"issue":"51","key":"e_1_3_2_41_2","first-page":"1","article-title":"An open source chemical structure curation pipeline using RDKit","volume":"12","author":"Bento A. Patr\u00edcia","year":"2020","unstructured":"A. Patr\u00edcia Bento, Anne Hersey, Eloy F\u00e9lix, Greg Landrum, Anna Gaulton, Francis Atkinson, Louisa J. Bellis, Marleen De Veij, and Andrew R. Leach. 2020. An open source chemical structure curation pipeline using RDKit. Journal of Cheminformatics 12, 51 (2020), 1\u201316.","journal-title":"Journal of Cheminformatics"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1021\/ci00062a008"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu626"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"e_1_3_2_45_2","unstructured":"Bharath Ramsundar Steven Kearnes Patrick Riley Dale Webster David Konerding and Vijay Pande. 2015. Massively multitask networks for drug discovery. arXiv:1502.02072. Retrieved from https:\/\/arxiv.org\/abs\/1502.02072"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"e_1_3_2_47_2","volume-title":"Proceedings of International Conference on Learning Representations","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of International Conference on Learning Representations."},{"key":"e_1_3_2_48_2","first-page":"1","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Sch\u00fctt Kristof","year":"2017","unstructured":"Kristof Sch\u00fctt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, and Klaus-Robert M\u00fcller. 2017. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. In Proceedings of Advances in Neural Information Processing Systems, 1\u201311."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011052"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"e_1_3_2_51_2","unstructured":"\u0141ukasz Maziarka Tomasz Danel S\u0142awomir Mucha Krzysztof Rataj Jacek Tabor and Stanis\u0142aw Jastrz\u011bbski. 2020. Molecule attention transformer. arXiv:2002.08264. Retrieved from https:\/\/arxiv.org\/abs\/2002.08264"},{"issue":"3","key":"e_1_3_2_52_2","first-page":"1","article-title":"Relative molecule self-attention transformer","volume":"16","author":"Maziarka \u0141ukasz","year":"2024","unstructured":"\u0141ukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gai\u0144ski, Jacek Tabor, Igor Podolak, Pawe\u0142 Morkisz, and Stanis\u0142aw Jastrz\u0119bski. 2024. Relative molecule self-attention transformer. Journal of Cheminformatics 16, 3 (2024), 1\u201314.","journal-title":"Journal of Cheminformatics"},{"issue":"11","key":"e_1_3_2_53_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten Laurens","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008), 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/329412"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.arabjc.2022.104242"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jen.2006.05.012"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T10:45:50Z","timestamp":1772966750000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3787204"],"URL":"https:\/\/doi.org\/10.1145\/3787204","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2024-09-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}