{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T06:17:13Z","timestamp":1778998633755,"version":"3.51.4"},"reference-count":220,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T00:00:00Z","timestamp":1728518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"crossref","award":["LP210301259, and DP230100899"],"award-info":[{"award-number":["LP210301259, and DP230100899"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>Graphs have a superior ability to represent relational data, such as chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as input, has been applied to many tasks, including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures. While these methods benefit from good interpretability, they often suffer from computational bottlenecks, as they cannot skirt the graph isomorphism problem. Conversely, deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations. As a result, these deep graph learning methods have been responsible for many successes. Yet, no comprehensive survey reviews graph-level learning starting with traditional learning and moving through to the deep learning approaches. This article fills this gap and frames the representative algorithms into a systematic taxonomy covering traditional learning, graph-level deep neural networks, graph-level graph neural networks, and graph pooling. In addition, the evolution and interaction between methods from these four branches within their developments are examined to provide an in-depth analysis. This is followed by a brief review of the benchmark datasets, evaluation metrics, and common downstream applications. Finally, the survey concludes with an in-depth discussion of 12 current and future directions in this booming field.<\/jats:p>","DOI":"10.1145\/3695863","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T03:43:40Z","timestamp":1726199020000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["State of the Art and Potentialities of Graph-level Learning"],"prefix":"10.1145","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6588-3014","authenticated-orcid":false,"given":"Zhenyu","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6009-780X","authenticated-orcid":false,"given":"Ge","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing, Donghua University, Shanghai, China and School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1371-5801","authenticated-orcid":false,"given":"Jia","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4408-1952","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3326-4147","authenticated-orcid":false,"given":"Quan Z.","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9123-5133","authenticated-orcid":false,"given":"Shan","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9958-8673","authenticated-orcid":false,"given":"Chuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2579-7581","authenticated-orcid":false,"given":"Charu","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Office 4S-A20, IBM T. J. Watson Research Center, Hawthorne, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0458-5977","authenticated-orcid":false,"given":"Hao","family":"Peng","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9258-3850","authenticated-orcid":false,"given":"Wenbin","family":"Hu","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4496-2028","authenticated-orcid":false,"given":"Edwin","family":"Hancock","sequence":"additional","affiliation":[{"name":"University of York, York, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0540-5053","authenticated-orcid":false,"given":"Pietro","family":"Li\u00f2","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, United Kingdom of Great Britain and Northern Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,10]]},"reference":[{"key":"e_1_3_3_2_2","first-page":"128","article-title":"Solutio problematis ad geometriam situs pertinentis","author":"Euler Leonhard","year":"1741","unstructured":"Leonhard Euler. 1741. Solutio problematis ad geometriam situs pertinentis. Comment. Acad. Sci. Imp. Petropol. (1741), 128\u2013140.","journal-title":"Comment. Acad. Sci. Imp. Petropol."},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"e_1_3_3_4_2","first-page":"1","volume-title":"ICLR","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? In ICLR. 1\u201317."},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"e_1_3_3_6_2","first-page":"1","volume-title":"NeurIPS","author":"Maron Haggai","year":"2019","unstructured":"Haggai Maron, Heli Ben-Hamu, Hadar Serviansky, and Yaron Lipman. 2019. Provably powerful graph networks. In NeurIPS. 1\u201312."},{"key":"e_1_3_3_7_2","first-page":"12559","volume-title":"NeurIPS","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 NeurIPS, Vol. 33. 12559\u201312571."},{"key":"e_1_3_3_8_2","first-page":"610","volume-title":"ICML","author":"Bojchevski Aleksandar","year":"2018","unstructured":"Aleksandar Bojchevski, Oleksandr Shchur, Daniel Z\u00fcgner, and Stephan G\u00fcnnemann. 2018. NetGAN: Generating graphs via random walks. In ICML. 610\u2013619."},{"key":"e_1_3_3_9_2","first-page":"5708","volume-title":"ICML","author":"You Jiaxuan","year":"2018","unstructured":"Jiaxuan You, Rex Ying, Xiang Ren, William Hamilton, and Jure Leskovec. 2018. GraphRNN: Generating realistic graphs with deep auto-regressive models. In ICML. 5708\u20135717."},{"key":"e_1_3_3_10_2","unstructured":"Frank Harary. 1969. The four color conjecture and other graphical diseases. Proof Techniques in Graph Theory 1 1 (1969) 1\u20139."},{"issue":"9","key":"e_1_3_3_11_2","first-page":"12","article-title":"The reduction of a graph to canonical form and the algebra which appears therein","volume":"2","author":"Weisfeiler Boris","year":"1968","unstructured":"Boris Weisfeiler and Andrei Leman. 1968. The reduction of a graph to canonical form and the algebra which appears therein. NTI, Series 2, 9 (1968), 12\u201316.","journal-title":"NTI, Series"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsc.2013.09.003"},{"key":"e_1_3_3_13_2","first-page":"684","volume-title":"STOC","author":"Babai L\u00e1szl\u00f3","year":"2016","unstructured":"L\u00e1szl\u00f3 Babai. 2016. Graph isomorphism in quasipolynomial time. In STOC. 684\u2013697."},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45167-9_11"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45372-5_2"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00447-x"},{"key":"e_1_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Jessica Vamathevan Dominic Clark Paul Czodrowski Ian Dunham Edgardo Ferran George Lee Bin Li Anant Madabhushi Parantu Shah Michaela Spitzer and Shanrong Zhao. 2019. Applications of machine learning in drug discovery and development. Nat. Rev. Drug Discov 18 6 (2019) 463\u2013477.","DOI":"10.1038\/s41573-019-0024-5"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403383"},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Xuexiong Luo Jia Wu Jian Yang Hongyang Chen Zhao Li Hao Peng and Chuan Zhou. 2024. Knowledge distillation guided interpretable brain subgraph neural networks for brain disorder exploration. IEEE Trans. Neural Netw. Learn. Syst. 1 1 (2024) 1\u201314.","DOI":"10.1109\/TNNLS.2023.3341802"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Ziwei Zhang Peng Cui and Wenwu Zhu. 2020. Deep learning on graphs: A survey. IEEE Trans. Knowl. Data Eng. 34 1 (2020) 249\u2013270.","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41109-019-0195-3"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/752"},{"key":"e_1_3_3_24_2","doi-asserted-by":"crossref","unstructured":"Daniele Grattarola Daniele Zambon Filippo Maria Bianchi and Cesare Alippi. 2022. Understanding pooling in graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 35 2 (2022) 2708\u20132718.","DOI":"10.1109\/TNNLS.2022.3190922"},{"key":"e_1_3_3_25_2","first-page":"5724","volume-title":"NeurIPS","author":"Du Simon S.","year":"2019","unstructured":"Simon S. Du, Kangcheng Hou, Ruslan Salakhutdinov, Barnab\u00e1s P\u00f3czos, Ruosong Wang, and Keyulu Xu. 2019. Graph neural tangent kernel: Fusing graph neural networks with graph kernels. In NeurIPS. 5724\u20135734."},{"key":"e_1_3_3_26_2","first-page":"1263","volume-title":"ICML","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 ICML. 1263\u20131272."},{"key":"e_1_3_3_27_2","unstructured":"David Haussler. 1999. Convolution kernels on discrete structures. Citeseer."},{"issue":"9","key":"e_1_3_3_28_2","article-title":"Weisfeiler-Lehman graph kernels.","volume":"12","author":"Shervashidze Nino","year":"2011","unstructured":"Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M. Borgwardt. 2011. Weisfeiler-Lehman graph kernels. J. Mach. Learn. Res. 12, 9 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2009.30"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.42"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-015-5517-9"},{"key":"e_1_3_3_32_2","first-page":"5448","volume-title":"ICML","author":"Rieck Bastian","year":"2019","unstructured":"Bastian Rieck, Christian Bock, and Karsten Borgwardt. 2019. A persistent Weisfeiler-Lehman procedure for graph classification. In ICML. 5448\u20135458."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2005.132"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1202"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015446"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859891"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102380"},{"key":"e_1_3_3_38_2","first-page":"1860","volume-title":"NeurIPS","author":"Pachauri Deepti","year":"2013","unstructured":"Deepti Pachauri, Risi Kondor, and Vikas Singh. 2013. Solving the multi-way matching problem by permutation synchronization. In NeurIPS. 1860\u20131868."},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783341"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_12"},{"key":"e_1_3_3_41_2","first-page":"488","volume-title":"AISTATS","author":"Shervashidze Nino","year":"2009","unstructured":"Nino Shervashidze, S. V. N. Vishwanathan, Tobias Petri, Kurt Mehlhorn, and Karsten Borgwardt. 2009. Efficient graphlet kernels for large graph comparison. In AISTATS. 488\u2013495."},{"key":"e_1_3_3_42_2","first-page":"255","volume-title":"ICML","author":"Costa Fabrizio","year":"2010","unstructured":"Fabrizio Costa and Kurt De Grave. 2010. Fast neighborhood subgraph pairwise distance kernel. In ICML. 255\u2013262."},{"key":"e_1_3_3_43_2","first-page":"291","volume-title":"ICML","author":"Kriege Nils","year":"2012","unstructured":"Nils Kriege and Petra Mutzel. 2012. Subgraph matching kernels for attributed graphs. In ICML. 291\u2013298."},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.5555\/645496.658027"},{"key":"e_1_3_3_45_2","first-page":"721","volume-title":"ICDM","author":"Yan Xifeng","year":"2002","unstructured":"Xifeng Yan and Jiawei Han. 2002. gSpan: Graph-based substructure pattern mining. In ICDM. 721\u2013724."},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376662"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972795.92"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.58"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835905"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2011.119"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2014.97"},{"key":"e_1_3_3_52_2","first-page":"87","volume-title":"NeurIPS","author":"Verma Saurabh","year":"2017","unstructured":"Saurabh Verma and Zhi-Li Zhang. 2017. Hunt for the unique, stable, sparse and fast feature learning on graphs. In NeurIPS. 87\u201397."},{"key":"e_1_3_3_53_2","first-page":"2186","volume-title":"ICML","author":"Ivanov Sergey","year":"2018","unstructured":"Sergey Ivanov and Evgeny Burnaev. 2018. Anonymous walk embeddings. In ICML. 2186\u20132195."},{"key":"e_1_3_3_54_2","article-title":"A simple yet effective baseline for non-attribute graph classification","author":"Cai Chen","year":"2018","unstructured":"Chen Cai and Yusu Wang. 2018. A simple yet effective baseline for non-attribute graph classification. arXiv preprint arXiv:1811.03508 (2018).","journal-title":"arXiv preprint arXiv:1811.03508"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380026"},{"key":"e_1_3_3_56_2","first-page":"3699","volume-title":"WWW","author":"Liu Xuecheng","year":"2021","unstructured":"Xuecheng Liu, Luoyi Fu, and Xinbing Wang. 2021. Bridging the gap between von Neumann graph entropy and structural information: Theory and applications. In WWW. 3699\u20133710."},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00067"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/367766.368168"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13672-6_37"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0103-5"},{"key":"e_1_3_3_62_2","volume-title":"Spectral Graph Theory","author":"Chung Fan R. K.","year":"1997","unstructured":"Fan R. K. Chung and Fan Chung Graham. 1997. Spectral Graph Theory. Vol. 92. American Mathematical Society."},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00026-006-0289-3"},{"key":"e_1_3_3_64_2","first-page":"1091","volume-title":"ICML","author":"Chen Pin-Yu","year":"2019","unstructured":"Pin-Yu Chen, Lingfei Wu, Sijia Liu, and Indika Rajapakse. 2019. Fast incremental von Neumann graph entropy computation: Theory, algorithm, and applications. In ICML. 1091\u20131101."},{"key":"e_1_3_3_65_2","volume-title":"KDD Workshop on Mining and Learning with Graphs","author":"Narayanan Annamalai","year":"2016","unstructured":"Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu, and Santhoshkumar Saminathan. 2016. subgraph2vec: Learning distributed representations of rooted sub-graphs from large graphs. In KDD Workshop on Mining and Learning with Graphs."},{"key":"e_1_3_3_66_2","volume-title":"KDD Workshop on Mining and Learning with Graphs","author":"Narayanan Annamalai","year":"2017","unstructured":"Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan, Lihui Chen, Yang Liu, and Shantanu Jaiswal. 2017. graph2vec: Learning distributed representations of graphs. In KDD Workshop on Mining and Learning with Graphs."},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975321.35"},{"key":"e_1_3_3_68_2","first-page":"1","volume-title":"ICLR","author":"Li Yujia","year":"2016","unstructured":"Yujia Li, Richard Zemel, Marc Brockschmidt, and Daniel Tarlow. 2016. Gated graph sequence neural networks. In ICLR. 1\u201320."},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11742"},{"key":"e_1_3_3_71_2","first-page":"2014","volume-title":"ICML","author":"Niepert Mathias","year":"2016","unstructured":"Mathias Niepert, Mohamed Ahmed, and Konstantin Kutzkov. 2016. Learning convolutional neural networks for graphs. In ICML. 2014\u20132023."},{"key":"e_1_3_3_72_2","first-page":"1993","volume-title":"NeurIPS","author":"Atwood James","year":"2016","unstructured":"James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In NeurIPS. 1993\u20132001."},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_3"},{"key":"e_1_3_3_75_2","first-page":"1","volume-title":"ICML-IJCAL Workshop on Computational Biology","author":"Verma Saurabh","year":"2018","unstructured":"Saurabh Verma and Zhi-Li Zhang. 2018. Graph capsule convolutional neural networks. In ICML-IJCAL Workshop on Computational Biology. 1\u201312."},{"key":"e_1_3_3_76_2","first-page":"1","volume-title":"ICLR","author":"Xinyi Zhang","year":"2018","unstructured":"Zhang Xinyi and Lihui Chen. 2018. Capsule graph neural network. In ICLR. 1\u201316."},{"key":"e_1_3_3_77_2","article-title":"Capsule neural networks for graph classification using explicit tensorial graph representations","author":"Mallea Marcelo Daniel Gutierrez","year":"2019","unstructured":"Marcelo Daniel Gutierrez Mallea, Peter Meltzer, and Peter J. Bentley. 2019. Capsule neural networks for graph classification using explicit tensorial graph representations. arXiv preprint arXiv:1902.08399 (2019).","journal-title":"arXiv preprint arXiv:1902.08399"},{"key":"e_1_3_3_78_2","first-page":"1","volume-title":"AAAI Workshop on Deep Learning on Graphs: Methods and Applications","author":"Dwivedi Vijay Prakash","year":"2020","unstructured":"Vijay Prakash Dwivedi and Xavier Bresson. 2020. A generalization of transformer networks to graphs. In AAAI Workshop on Deep Learning on Graphs: Methods and Applications. 1\u20138."},{"key":"e_1_3_3_79_2","first-page":"28877","volume-title":"NeurIPS","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 NeurIPS, Vol. 34. 28877\u201328888."},{"key":"e_1_3_3_80_2","first-page":"14582","volume-title":"NeurIPS","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 NeurIPS, Vol. 35. 14582\u201314595."},{"key":"e_1_3_3_81_2","first-page":"1","volume-title":"ICLR","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In ICLR. 1\u201312."},{"key":"e_1_3_3_82_2","first-page":"2873","volume-title":"IJCAI","author":"Liu Pengfei","year":"2016","unstructured":"Pengfei Liu, Xipeng Qiu, and Xuanjing Huang. 2016. Recurrent neural network for text classification with multi-task learning. In IJCAI. 2873\u20132879."},{"key":"e_1_3_3_83_2","doi-asserted-by":"crossref","unstructured":"Geoffrey Hinton Li Deng Dong Yu George E. Dahl Abdel-rahman Mohamed Navdeep Jaitly Andrew Senior Vincent Vanhoucke Patrick Nguyen Tara N. Sainath and Brian Kingsbury. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Process. Mag. 29 6 (2012) 82\u201397.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.wasman.2024.02.014"},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2010350"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.5555\/2029556.2029562"},{"key":"e_1_3_3_89_2","first-page":"1","volume-title":"NeurIPS","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 NeurIPS, Vol. 30. Curran Associates, Inc., 1\u201311."},{"key":"e_1_3_3_90_2","volume-title":"ICLR","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, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR."},{"key":"e_1_3_3_91_2","first-page":"2224","volume-title":"NeurIPS","author":"Duvenaud David K.","year":"2015","unstructured":"David K. Duvenaud, Dougal Maclaurin, Jorge Iparraguirre, Rafael Bombarell, Timothy Hirzel, Al\u00e1n Aspuru-Guzik, and Ryan P. Adams. 2015. Convolutional networks on graphs for learning molecular fingerprints. In NeurIPS. 2224\u20132232."},{"key":"e_1_3_3_92_2","first-page":"4502","volume-title":"NeurIPS","author":"Battaglia Peter W.","year":"2016","unstructured":"Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, and Koray Kavukcuoglu. 2016. Interaction networks for learning about objects, relations and physics. In NeurIPS. 4502\u20134510."},{"key":"e_1_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13890"},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"e_1_3_3_95_2","first-page":"4663","volume-title":"ICML","author":"Murphy Ryan","year":"2019","unstructured":"Ryan Murphy, Balasubramaniam Srinivasan, Vinayak Rao, and Bruno Ribeiro. 2019. Relational pooling for graph representations. In ICML. 4663\u20134673."},{"key":"e_1_3_3_96_2","first-page":"1","volume-title":"ICLR","author":"Azizian Waiss","year":"2021","unstructured":"Waiss Azizian and Marc Lelarge. 2021. Expressive power of invariant and equivariant graph neural networks. In ICLR. 1\u201339."},{"key":"e_1_3_3_97_2","first-page":"1026","volume-title":"ICML","author":"Bodnar Cristian","year":"2021","unstructured":"Cristian Bodnar, Fabrizio Frasca, Yuguang Wang, Nina Otter, Guido F. Montufar, Pietro Lio, and Michael Bronstein. 2021. Weisfeiler and Lehman go topological: Message passing simplicial networks. In ICML. 1026\u20131037."},{"key":"e_1_3_3_98_2","first-page":"2625","volume-title":"NeurIPS","author":"Bodnar Cristian","year":"2021","unstructured":"Cristian Bodnar, Fabrizio Frasca, Nina Otter, Yuguang Wang, Pietro Lio, Guido F. Montufar, and Michael Bronstein. 2021. Weisfeiler and Lehman go cellular: CW networks. In NeurIPS. 2625\u20132640."},{"key":"e_1_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/291"},{"key":"e_1_3_3_100_2","first-page":"1","volume-title":"NeurIPS","author":"Alsentzer Emily","year":"2020","unstructured":"Emily Alsentzer, Samuel G. Finlayson, Michelle M. Li, and Marinka Zitnik. 2020. Subgraph neural networks. In NeurIPS. 1\u201313."},{"key":"e_1_3_3_101_2","first-page":"2081","volume-title":"WWW","author":"Sun Qingyun","year":"2021","unstructured":"Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Yuanxing Ning, Philip S. Yu, and Lifang He. 2021. SUGAR: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In WWW. 2081\u20132091."},{"key":"e_1_3_3_102_2","first-page":"1","volume-title":"NeurIPS","author":"Zhang Muhan","year":"2021","unstructured":"Muhan Zhang and Pan Li. 2021. Nested Graph neural networks. In NeurIPS. 1\u201314."},{"key":"e_1_3_3_103_2","first-page":"1","volume-title":"ICLR","author":"Zhao Lingxiao","year":"2022","unstructured":"Lingxiao Zhao, Wei Jin, Leman Akoglu, and Neil Shah. 2022. From stars to subgraphs: Uplifting any GNN with local structure awareness. In ICLR. 1\u201322."},{"key":"e_1_3_3_104_2","first-page":"1","volume-title":"ICLR","author":"Wijesinghe Asiri","year":"2022","unstructured":"Asiri Wijesinghe and Qing Wang. 2022. A new perspective on \u201chow graph neural networks go beyond Weisfeiler-Lehman?\u201d In ICLR. 1\u201323."},{"key":"e_1_3_3_105_2","first-page":"1","volume-title":"ICLR","author":"Bevilacqua Beatrice","year":"2022","unstructured":"Beatrice Bevilacqua, Fabrizio Frasca, Derek Lim, Balasubramaniam Srinivasan, Chen Cai, Gopinath Balamurugan, Michael M. Bronstein, and Haggai Maron. 2022. Equivariant subgraph aggregation networks. In ICLR. 1\u201346."},{"key":"e_1_3_3_106_2","doi-asserted-by":"crossref","unstructured":"Giorgos Bouritsas Fabrizio Frasca Stefanos P. Zafeiriou and Michael Bronstein. 2022. Improving graph neural network expressivity via subgraph isomorphism counting. IEEE Trans. Pattern Anal. Mach. Intell. 45 1 (2022) 657\u2013668.","DOI":"10.1109\/TPAMI.2022.3154319"},{"key":"e_1_3_3_107_2","volume-title":"ICLR","author":"Huang Yinan","year":"2023","unstructured":"Yinan Huang, Xingang Peng, Jianzhu Ma, and Muhan Zhang. 2023. Boosting the cycle counting power of graph neural networks with I$\u23032$-GNNs. In ICLR."},{"key":"e_1_3_3_108_2","first-page":"37","volume-title":"WWW","author":"Al-Rfou Rami","year":"2019","unstructured":"Rami Al-Rfou, Bryan Perozzi, and Dustin Zelle. 2019. DDGK: Learning graph representations for deep divergence graph kernels. In WWW. 37\u201348."},{"key":"e_1_3_3_109_2","first-page":"1576","volume-title":"ICML","author":"Chen Dexiong","year":"2020","unstructured":"Dexiong Chen, Laurent Jacob, and Julien Mairal. 2020. Convolutional kernel networks for graph-structured data. In ICML. 1576\u20131586."},{"key":"e_1_3_3_110_2","first-page":"16211","volume-title":"NeurIPS","author":"Nikolentzos Giannis","year":"2020","unstructured":"Giannis Nikolentzos and Michalis Vazirgiannis. 2020. Random walk graph neural networks. In NeurIPS. 16211\u201316222."},{"key":"e_1_3_3_111_2","first-page":"1204","volume-title":"WWW","author":"Long Qingqing","year":"2021","unstructured":"Qingqing Long, Yilun Jin, Yi Wu, and Guojie Song. 2021. Theoretically improving graph neural networks via anonymous walk graph kernels. In WWW. 1204\u20131214."},{"key":"e_1_3_3_112_2","first-page":"4776","volume-title":"NeurIPS","author":"Feng Jiarui","year":"2022","unstructured":"Jiarui Feng, Yixin Chen, Fuhai Li, Anindya Sarkar, and Muhan Zhang. 2022. How powerful are k-hop message passing graph neural networks. In NeurIPS, Vol. 35. 4776\u20134790."},{"key":"e_1_3_3_113_2","first-page":"3837","volume-title":"NeurIPS","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS. 3837\u20133845."},{"key":"e_1_3_3_114_2","first-page":"272","article-title":"Transferability of spectral graph convolutional neural networks.","volume":"22","author":"Levie Ron","year":"2021","unstructured":"Ron Levie, Wei Huang, Lorenzo Bucci, Michael M. Bronstein, and Gitta Kutyniok. 2021. Transferability of spectral graph convolutional neural networks. J. Mach. Learn. Res. 22 (2021), 272\u2013331.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_115_2","first-page":"599","volume-title":"ICML","author":"Balcilar Muhammet","year":"2021","unstructured":"Muhammet Balcilar, Pierre H\u00e9roux, Benoit Gauzere, Pascal Vasseur, S\u00e9bastien Adam, and Paul Honeine. 2021. Breaking the limits of message passing graph neural networks. In ICML. 599\u2013608."},{"key":"e_1_3_3_116_2","doi-asserted-by":"crossref","unstructured":"Filippo Maria Bianchi Daniele Grattarola Lorenzo Livi and Cesare Alippi. 2021. Graph neural networks with convolutional arma filters. IEEE Trans. Pattern Anal. Mach. Intell. 44 7 (2021) 3496\u20133507.","DOI":"10.1109\/TPAMI.2021.3054830"},{"key":"e_1_3_3_117_2","first-page":"1","volume-title":"ICML","author":"Zheng Xuebin","year":"2021","unstructured":"Xuebin Zheng, Bingxin Zhou, Junbin Gao, Yuguang Wang, Pietro Li\u00f3, Ming Li, and Guido Montufar. 2021. How framelets enhance graph neural networks. In ICML. 1\u201310."},{"key":"e_1_3_3_118_2","first-page":"14501","volume-title":"NeurIPS","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 NeurIPS, Vol. 35. 14501\u201314515."},{"key":"e_1_3_3_119_2","first-page":"1","volume-title":"ICLR","author":"Xu Keyulu","year":"2021","unstructured":"Keyulu Xu, Mozhi Zhang, Jingling Li, Simon Shaolei Du, Ken-Ichi Kawarabayashi, and Stefanie Jegelka. 2021. How neural networks extrapolate: From feedforward to graph neural networks. In ICLR. 1\u201352."},{"key":"e_1_3_3_120_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2020.04.003"},{"key":"e_1_3_3_121_2","first-page":"14143","volume-title":"NeurIPS","author":"Vignac Cl\u00e9ment","year":"2020","unstructured":"Cl\u00e9ment Vignac, Andreas Loukas, and Pascal Frossard. 2020. Building powerful and equivariant graph neural networks with structural message-passing. In NeurIPS. 14143\u201314155."},{"key":"e_1_3_3_122_2","first-page":"652","volume-title":"CVPR","author":"Qi Charles R.","year":"2017","unstructured":"Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep learning on point sets for 3D classification and segmentation. In CVPR. 652\u2013660."},{"key":"e_1_3_3_123_2","first-page":"1","volume-title":"NeurIPS","author":"Jacot Arthur","year":"2018","unstructured":"Arthur Jacot, Cl\u00e9ment Hongler, and Franck Gabriel. 2018. Neural tangent kernel: Convergence and generalization in neural networks. In NeurIPS. 1\u201310."},{"key":"e_1_3_3_124_2","first-page":"2024","volume-title":"ICML","author":"Lei Tao","year":"2017","unstructured":"Tao Lei, Wengong Jin, Regina Barzilay, and Tommi Jaakkola. 2017. Deriving neural architectures from sequence and graph kernels. In ICML. 2024\u20132033."},{"key":"e_1_3_3_125_2","first-page":"1","volume-title":"ICML","author":"Bruna Joan","year":"2014","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann Lecun. 2014. Spectral networks and locally connected networks on graphs. In ICML. 1\u201314."},{"key":"e_1_3_3_126_2","volume-title":"ICLR","author":"Balcilar Muhammet","year":"2020","unstructured":"Muhammet Balcilar, Guillaume Renton, Pierre H\u00e9roux, Benoit Ga\u00fcz\u00e8re, S\u00e9bastien Adam, and Paul Honeine. 2020. Analyzing the expressive power of graph neural networks in a spectral perspective. In ICLR."},{"key":"e_1_3_3_127_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"e_1_3_3_128_2","article-title":"Bridging the gap between spectral and spatial domains in graph neural networks","author":"Balcilar Muhammet","year":"2020","unstructured":"Muhammet Balcilar, Guillaume Renton, Pierre H\u00e9roux, Benoit Gauzere, Sebastien Adam, and Paul Honeine. 2020. Bridging the gap between spectral and spatial domains in graph neural networks. arXiv preprint arXiv:2003.11702 (2020).","journal-title":"arXiv preprint arXiv:2003.11702"},{"key":"e_1_3_3_129_2","first-page":"1","volume-title":"ICLR","author":"Xu Bingbing","year":"2019","unstructured":"Bingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, and Xueqi Cheng. 2019. Graph wavelet neural network. In ICLR. 1\u201313."},{"key":"e_1_3_3_130_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.04.005"},{"key":"e_1_3_3_131_2","first-page":"23341","volume-title":"ICML","author":"Wang Xiyuan","year":"2022","unstructured":"Xiyuan Wang and Muhan Zhang. 2022. How powerful are spectral graph neural networks. In ICML. 23341\u201323362."},{"key":"e_1_3_3_132_2","first-page":"3469","volume-title":"ICML","author":"Chen Dexiong","year":"2022","unstructured":"Dexiong Chen, Leslie O\u2019Bray, and Karsten Borgwardt. 2022. Structure-aware transformer for graph representation learning. In ICML. PMLR, 3469\u20133489."},{"key":"e_1_3_3_133_2","first-page":"1","volume-title":"NeurIPS","author":"Corso Gabriele","year":"2020","unstructured":"Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Li\u00f2, and Petar Veli\u010dkovi\u0107. 2020. Principal neighbourhood aggregation for graph nets. In NeurIPS. 1\u201311."},{"key":"e_1_3_3_134_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.31"},{"key":"e_1_3_3_135_2","doi-asserted-by":"crossref","unstructured":"Zhengyang Wang and Shuiwang Ji. 2020. Second-order pooling for graph neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 45 6 (2020) 1\u201312.","DOI":"10.1109\/TPAMI.2020.2999032"},{"key":"e_1_3_3_136_2","first-page":"1","volume-title":"ICLR","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Samy Bengio, and Manjunath Kudlur. 2016. Order matters: Sequence to sequence for sets. In ICLR. 1\u201311."},{"key":"e_1_3_3_137_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380083"},{"key":"e_1_3_3_138_2","article-title":"Deep convolutional networks on graph-structured data","author":"Henaff Mikael","year":"2015","unstructured":"Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015).","journal-title":"arXiv preprint arXiv:1506.05163"},{"key":"e_1_3_3_139_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"e_1_3_3_140_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330982"},{"key":"e_1_3_3_141_2","first-page":"1","volume-title":"ICLR","author":"Bruna Joan","year":"2014","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral networks and deep locally connected networks on graphs. In ICLR. 1\u201314."},{"key":"e_1_3_3_142_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_3_3_143_2","first-page":"1","volume-title":"ICLR","author":"Baek Jinheon","year":"2021","unstructured":"Jinheon Baek, Minki Kang, and Sung Ju Hwang. 2021. Accurate learning of graph representations with graph multiset pooling. In ICLR. 1\u201322."},{"key":"e_1_3_3_144_2","first-page":"874","volume-title":"ICML","author":"Bianchi Filippo Maria","year":"2020","unstructured":"Filippo Maria Bianchi, Daniele Grattarola, and Cesare Alippi. 2020. Spectral clustering with graph neural networks for graph pooling. In ICML. 874\u2013883."},{"key":"e_1_3_3_145_2","first-page":"4805","volume-title":"NeurIPS","author":"Ying Zhitao","year":"2018","unstructured":"Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. 2018. Hierarchical graph representation learning with differentiable pooling. In NeurIPS. 4805\u20134815."},{"key":"e_1_3_3_146_2","first-page":"1","volume-title":"ICLR","author":"Yuan Hao","year":"2020","unstructured":"Hao Yuan and Shuiwang Ji. 2020. StructPool: Structured graph pooling via conditional random fields. In ICLR. 1\u201312."},{"key":"e_1_3_3_147_2","first-page":"2083","volume-title":"ICML","author":"Gao Hongyang","year":"2019","unstructured":"Hongyang Gao and Shuiwang Ji. 2019. Graph U-Nets. In ICML. 2083\u20132092."},{"key":"e_1_3_3_148_2","article-title":"Towards sparse hierarchical graph classifiers","author":"Cangea C\u0103t\u0103lina","year":"2018","unstructured":"C\u0103t\u0103lina Cangea, Petar Veli\u010dkovi\u0107, Nikola Jovanovi\u0107, Thomas Kipf, and Pietro Li\u00f2. 2018. Towards sparse hierarchical graph classifiers. arXiv preprint arXiv:1811.01287 (2018).","journal-title":"arXiv preprint arXiv:1811.01287"},{"key":"e_1_3_3_149_2","first-page":"3734","volume-title":"ICML","author":"Lee Junhyun","year":"2019","unstructured":"Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-attention graph pooling. In ICML. 3734\u20133743."},{"key":"e_1_3_3_150_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5997"},{"key":"e_1_3_3_151_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11941"},{"key":"e_1_3_3_152_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"e_1_3_3_153_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1115"},{"key":"e_1_3_3_154_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3044146"},{"key":"e_1_3_3_155_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/497"},{"key":"e_1_3_3_156_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2555904"},{"key":"e_1_3_3_157_2","first-page":"24017","volume-title":"ICML","author":"Wu Junran","year":"2022","unstructured":"Junran Wu, Xueyuan Chen, Ke Xu, and Shangzhe Li. 2022. Structural entropy guided graph hierarchical pooling. In ICML. 24017\u201324030."},{"key":"e_1_3_3_158_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2024.104175"},{"key":"e_1_3_3_159_2","volume-title":"ICML","author":"Sun Li","year":"2024","unstructured":"Li Sun, Zhenhao Huang, Hao Peng, YuJie Wang, Chunyang Liu, and Philip S. Yu. 2024. LSEnet: Lorentz structural entropy neural network for deep graph clustering. In ICML."},{"key":"e_1_3_3_160_2","article-title":"Edge contraction pooling for graph neural networks","author":"Diehl Frederik","year":"2019","unstructured":"Frederik Diehl. 2019. Edge contraction pooling for graph neural networks. arXiv preprint arXiv:1905.10990 (2019).","journal-title":"arXiv preprint arXiv:1905.10990"},{"key":"e_1_3_3_161_2","article-title":"TUDataset: A collection of benchmark datasets for learning with graphs","author":"Morris Christopher","year":"2020","unstructured":"Christopher Morris, Nils M. Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann. 2020. TUDataset: A collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663 (2020).","journal-title":"arXiv preprint arXiv:2007.08663"},{"key":"e_1_3_3_162_2","first-page":"22118","volume-title":"NeurIPS","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 NeurIPS. 22118\u201322133."},{"key":"e_1_3_3_163_2","first-page":"1","volume-title":"NeurIPS Track Datasets and Benchmarks","author":"Freitas Scott","year":"2021","unstructured":"Scott Freitas, Yuxiao Dong, Joshua Neil, and Duen Horng Chau. 2021. A large-scale database for graph representation learning. In NeurIPS Track Datasets and Benchmarks. 1\u201313."},{"key":"e_1_3_3_164_2","article-title":"Benchmarking graph neural networks","author":"Dwivedi Vijay Prakash","year":"2020","unstructured":"Vijay Prakash Dwivedi, Chaitanya K. Joshi, Thomas Laurent, Yoshua Bengio, and Xavier Bresson. 2020. Benchmarking graph neural networks. arXiv preprint arXiv:2003.00982 (2020).","journal-title":"arXiv preprint arXiv:2003.00982"},{"key":"e_1_3_3_165_2","article-title":"Understanding isomorphism bias in graph data sets","author":"Ivanov Sergei","year":"2019","unstructured":"Sergei Ivanov, Sergei Sviridov, and Evgeny Burnaev. 2019. Understanding isomorphism bias in graph data sets. arXiv preprint arXiv:1910.12091 (2019).","journal-title":"arXiv preprint arXiv:1910.12091"},{"key":"e_1_3_3_166_2","first-page":"1912","volume-title":"CVPR","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In CVPR. 1912\u20131920."},{"key":"e_1_3_3_167_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"e_1_3_3_168_2","doi-asserted-by":"crossref","unstructured":"Paul D. Dobson and Andrew J. Doig. 2003. Distinguishing enzyme structures from non-enzymes without alignments. J. Mol. Biol. 330 4 (2003) 771\u2013783.","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"e_1_3_3_169_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00290"},{"key":"e_1_3_3_170_2","doi-asserted-by":"publisher","DOI":"10.1021\/ci8002649"},{"key":"e_1_3_3_171_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1818013116"},{"key":"e_1_3_3_172_2","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.6b00367"},{"key":"e_1_3_3_173_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chembiol.2016.07.023"},{"key":"e_1_3_3_174_2","doi-asserted-by":"publisher","DOI":"10.1021\/ci300124c"},{"key":"e_1_3_3_175_2","article-title":"Tox21 data challenge 2014","author":"Challenge TD","year":"2014","unstructured":"TD Challenge. 2014. Tox21 data challenge 2014. Retrieved from: https:\/\/tripod.nih.gov\/tox\/challenge","journal-title":"Retrieved from: https:\/\/tripod.nih.gov\/tox\/challenge"},{"key":"e_1_3_3_176_2","doi-asserted-by":"crossref","unstructured":"Ann M. Richard Richard S. Judson Keith A. Houck Christopher M. Grulke Patra Volarath Inthirany Thillainadarajah Chihae Yang James F. Rathman Matthew Thomas Martin John F. Wambaugh Thomas B. Knudsen Jayaram Kancherla Kamel Mansouri Grace Y. Patlewicz Antony John Williams Stephen B. Little Kevin M. Crofton and Russell S. Thomas. 2016. ToxCast chemical landscape: paving the road to 21st century toxicology. Chem. Res. Toxicol. 29 8 (2016) 1225\u20131251.","DOI":"10.1021\/acs.chemrestox.6b00135"},{"key":"e_1_3_3_177_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-014-9747-x"},{"key":"e_1_3_3_178_2","doi-asserted-by":"publisher","DOI":"10.1021\/ci034243x"},{"key":"e_1_3_3_179_2","unstructured":"M. Wenlock and N. Tomkinson. 2015. Experimental in vitro DMPK and physicochemical data on a set of publicly disclosed compounds."},{"key":"e_1_3_3_180_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0151-1"},{"key":"e_1_3_3_181_2","doi-asserted-by":"publisher","DOI":"10.1021\/ci3001277"},{"key":"e_1_3_3_182_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"e_1_3_3_183_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. Citeseer."},{"key":"e_1_3_3_184_2","article-title":"The MNIST database of handwritten digits","author":"LeCun Yann","year":"1998","unstructured":"Yann LeCun. 1998. The MNIST database of handwritten digits. Retrieved from: http:\/\/yann.lecun.com\/exdb\/mnist\/","journal-title":"Retrieved from: http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"e_1_3_3_185_2","article-title":"CodeSearchNet challenge: Evaluating the state of semantic code search","author":"Husain Hamel","year":"2019","unstructured":"Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt. 2019. CodeSearchNet challenge: Evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436 (2019).","journal-title":"arXiv preprint arXiv:1909.09436"},{"key":"e_1_3_3_186_2","first-page":"1","volume-title":"ICLR","author":"Ruffinelli Daniel","year":"2019","unstructured":"Daniel Ruffinelli, Samuel Broscheit, and Rainer Gemulla. 2019. You can teach an old dog new tricks! On training knowledge graph embeddings. In ICLR. 1\u201320."},{"key":"e_1_3_3_187_2","first-page":"1","volume-title":"ICLR","author":"Errica Federico","year":"2020","unstructured":"Federico Errica, Marco Podda, Davide Bacciu, and Alessio Micheli. 2020. A fair comparison of graph neural networks for graph classification. In ICLR. 1\u201316."},{"key":"e_1_3_3_188_2","first-page":"1","volume-title":"NeurIPS Track Datasets and Benchmarks","author":"Zhu Yanqiao","year":"2021","unstructured":"Yanqiao Zhu, Yichen Xu, Qiang Liu, and Shu Wu. 2021. An empirical study of graph contrastive learning. In NeurIPS Track Datasets and Benchmarks. 1\u201325."},{"key":"e_1_3_3_189_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-015-0872-1"},{"issue":"7","key":"e_1_3_3_190_2","first-page":"3236","article-title":"Multiple structure-view learning for graph classification","volume":"29","author":"Wu Jia","year":"2017","unstructured":"Jia Wu, Shirui Pan, Xingquan Zhu, Chengqi Zhang, and Philip S. Yu. 2017. Multiple structure-view learning for graph classification. IEEE Trans. Neural Netw. Learn. Syst. 29, 7 (2017), 3236\u20133251.","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"e_1_3_3_191_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570467"},{"key":"e_1_3_3_192_2","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"Bronstein Michael M.","year":"2021","unstructured":"Michael M. Bronstein, Joan Bruna, Taco Cohen, and Petar Veli\u010dkovi\u0107. 2021. Geometric deep learning: Grids, groups, graphs, geodesics, and gauges. arXiv preprint arXiv:2104.13478 (2021).","journal-title":"arXiv preprint arXiv:2104.13478"},{"key":"e_1_3_3_193_2","first-page":"9323","volume-title":"ICML","author":"Satorras V\u0131ctor Garcia","year":"2021","unstructured":"V\u0131ctor Garcia Satorras, Emiel Hoogeboom, and Max Welling. 2021. E(n) equivariant graph neural networks. In ICML. 9323\u20139332."},{"key":"e_1_3_3_194_2","first-page":"1","volume-title":"NeurIPS","author":"Gasteiger Johannes","year":"2021","unstructured":"Johannes Gasteiger, Florian Becker, and Stephan G\u00fcnnemann. 2021. GemNet: Universal directional graph neural networks for molecules. In NeurIPS. 1\u201313."},{"key":"e_1_3_3_195_2","volume-title":"ICLR","author":"Th\u00fcrlemann Moritz","year":"2022","unstructured":"Moritz Th\u00fcrlemann and Sereina Riniker. 2022. Anisotropic message passing: Graph neural networks with directional and long-range interactions. In ICLR."},{"key":"e_1_3_3_196_2","first-page":"19620","volume-title":"NeurIPS","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 NeurIPS. 19620\u201319631."},{"key":"e_1_3_3_197_2","first-page":"1","volume-title":"ICML","author":"Miao Siqi","year":"2022","unstructured":"Siqi Miao, Mia Liu, and Pan Li. 2022. Interpretable and generalizable graph learning via stochastic attention mechanism. In ICML. 1\u201320."},{"key":"e_1_3_3_198_2","first-page":"1","volume-title":"ICLR","author":"Azzolin Steve","year":"2023","unstructured":"Steve Azzolin, Antonio Longa, Pietro Barbiero, Pietro Lio, and Andrea Passerini. 2023. Global explainability of GNNs via logic combination of learned concepts. In ICLR. 1\u201316."},{"key":"e_1_3_3_199_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403085"},{"key":"e_1_3_3_200_2","first-page":"18839","volume-title":"NeurIPS","author":"Xie Han","year":"2021","unstructured":"Han Xie, Jing Ma, Li Xiong, and Carl Yang. 2021. Federated graph classification over non-IID graphs. In NeurIPS. 18839\u201318852."},{"key":"e_1_3_3_201_2","first-page":"1","volume-title":"NeurIPS","author":"Zhang Ge","year":"2022","unstructured":"Ge Zhang, Zhenyu Yang, Jia Wu, Jian Yang, Xue Shan, Hao Peng, Jianlin Su, Chuan Zhou, Quan Z. Sheng, Leman Akoglu, and Charu C. Aggarwal. 2022. Dual-discriminative graph neural network for imbalanced graph-level anomaly detection. In NeurIPS. 1\u201312."},{"key":"e_1_3_3_202_2","first-page":"379","volume-title":"AAAI","author":"Agarwal Puneet","year":"2012","unstructured":"Puneet Agarwal, Rajgopal Vaithiyanathan, Saurabh Sharma, and Gautam Shroff. 2012. Catching the long-tail: Extracting local news events from Twitter. In AAAI. 379\u2013382."},{"key":"e_1_3_3_203_2","article-title":"Imbalanced graph classification via graph-of-graph neural networks","author":"Wang Yu","year":"2021","unstructured":"Yu Wang, Yuying Zhao, Neil Shah, and Tyler Derr. 2021. Imbalanced graph classification via graph-of-graph neural networks. arXiv preprint arXiv:2112.00238 (2021).","journal-title":"arXiv preprint arXiv:2112.00238"},{"key":"e_1_3_3_204_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599374"},{"key":"e_1_3_3_205_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671929"},{"key":"e_1_3_3_206_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00036"},{"key":"e_1_3_3_207_2","first-page":"437","volume-title":"CIKM","author":"Hussein Rana","year":"2018","unstructured":"Rana Hussein, Dingqi Yang, and Philippe Cudr\u00e9-Mauroux. 2018. Are meta-paths necessary? Revisiting heterogeneous graph embeddings. In CIKM. 437\u2013446."},{"key":"e_1_3_3_208_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3101356"},{"key":"e_1_3_3_209_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2023.3309847"},{"key":"e_1_3_3_210_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411953"},{"key":"e_1_3_3_211_2","first-page":"1","volume-title":"IJCAI","author":"Wang Hanchen","year":"2021","unstructured":"Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, and Xuemin Lin. 2021. GoGNN: Graph of graphs neural network for predicting structured entity interactions. In IJCAI. 1\u20137."},{"key":"e_1_3_3_212_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/305"},{"key":"e_1_3_3_213_2","first-page":"1","article-title":"On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights","author":"Zhao Lingxiao","year":"2021","unstructured":"Lingxiao Zhao and Leman Akoglu. 2021. On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights. Big Data 11, 3 (2021), 1\u201330.","journal-title":"Big Data"},{"key":"e_1_3_3_214_2","first-page":"4393","volume-title":"ICML","author":"Ruff Lukas","year":"2018","unstructured":"Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel M\u00fcller, and Marius Kloft. 2018. Deep one-class classification. In ICML. 4393\u20134402."},{"key":"e_1_3_3_215_2","first-page":"21076","volume-title":"ICML","author":"Tang Jianheng","year":"2022","unstructured":"Jianheng Tang, Jiajin Li, Ziqi Gao, and Jia Li. 2022. Rethinking graph neural networks for anomaly detection. In ICML. 21076\u201321089."},{"key":"e_1_3_3_216_2","first-page":"1","volume-title":"ICLR","author":"Wu Ying-Xin","year":"2022","unstructured":"Ying-Xin Wu, Xiang Wang, An Zhang, Xiangnan He, and Tat-Seng Chua. 2022. Discovering invariant rationales for graph neural networks. In ICLR. 1\u201322."},{"key":"e_1_3_3_217_2","first-page":"1","volume-title":"ICML","author":"Bevilacqua Beatrice","year":"2021","unstructured":"Beatrice Bevilacqua, Yangze Zhou, and Bruno Ribeiro. 2021. Size-invariant graph representations for graph classification extrapolations. In ICML. 1\u201314."},{"key":"e_1_3_3_218_2","article-title":"GOOD: A graph out-of-distribution benchmark","author":"Gui Shurui","year":"2022","unstructured":"Shurui Gui, Xiner Li, Limei Wang, and Shuiwang Ji. 2022. GOOD: A graph out-of-distribution benchmark. arXiv preprint arXiv:2206.08452 (2022).","journal-title":"arXiv preprint arXiv:2206.08452"},{"key":"e_1_3_3_219_2","doi-asserted-by":"crossref","unstructured":"Olaf Sporns. 2022. Graph theory methods: Applications in brain networks. Dialogues Clin. Neurosci. 20 2 (2022).","DOI":"10.31887\/DCNS.2018.20.2\/osporns"},{"issue":"3","key":"e_1_3_3_220_2","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1109\/TCYB.2014.2327111","article-title":"Boosting for multi-graph classification","volume":"45","author":"Wu Jia","year":"2014","unstructured":"Jia Wu, Shirui Pan, Xingquan Zhu, and Zhihua Cai. 2014. Boosting for multi-graph classification. IEEE Trans. Cybern. 45, 3 (2014), 416\u2013429.","journal-title":"IEEE Trans. Cybern."},{"key":"e_1_3_3_221_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2788430"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695863","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:29Z","timestamp":1750291469000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695863"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,10]]},"references-count":220,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3695863"],"URL":"https:\/\/doi.org\/10.1145\/3695863","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,10]]},"assertion":[{"value":"2023-05-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}