{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:42:24Z","timestamp":1776879744716,"version":"3.51.2"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2045"],"award-info":[{"award-number":["U20B2045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192784"],"award-info":[{"award-number":["62192784"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322203"],"award-info":[{"award-number":["62322203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172052"],"award-info":[{"award-number":["62172052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002029"],"award-info":[{"award-number":["62002029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62141607"],"award-info":[{"award-number":["62141607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936219"],"award-info":[{"award-number":["U1936219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018AAA0102004"],"award-info":[{"award-number":["2018AAA0102004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tpami.2023.3321097","type":"journal-article","created":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:52:54Z","timestamp":1696269174000},"page":"322-337","source":"Crossref","is-referenced-by-count":69,"title":["Generalizing Graph Neural Networks on Out-of-Distribution Graphs"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1224-4243","authenticated-orcid":false,"given":"Shaohua","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4444-7811","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3734-0266","authenticated-orcid":false,"given":"Chuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2957-8511","authenticated-orcid":false,"given":"Peng","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4592-795X","authenticated-orcid":false,"given":"Bai","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref3","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref4","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref5","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref6","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"},{"key":"ref8","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref11","first-page":"1","article-title":"A PAC-Bayesian approach to generalization bounds for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liao"},{"key":"ref12","article-title":"A meta-transfer objective for learning to disentangle causal mechanisms","author":"Bengio","year":"2019"},{"key":"ref13","first-page":"1802","article-title":"Exploring the landscape of spatial robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engstrom"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref15","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref16","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","author":"Sun","year":"2020","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref17","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krueger"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.14"},{"key":"ref21","first-page":"4839","article-title":"Hierarchical generation of molecular graphs using structural motifs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref24","first-page":"5165","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330673"},{"key":"ref26","first-page":"1","article-title":"Beyond homophily: Reconstructing structure for graph-agnostic clustering","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pan"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380079"},{"key":"ref28","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3081010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3193725"},{"key":"ref31","first-page":"1","article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref32","first-page":"22 131","article-title":"Learning causally invariant representations for out-of-distribution generalization on graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref33","first-page":"11828","article-title":"Learning invariant graph representations for out-of-distribution generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref34","first-page":"24 934","article-title":"Debiasing graph neural networks via learning disentangled causal substructure","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref35","first-page":"12964","article-title":"Learning substructure invariance for out-of-distribution molecular representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref37","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref38","first-page":"1","article-title":"The risks of invariant risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rosenfeld"},{"key":"ref39","first-page":"4069","article-title":"Does invariant risk minimization capture invariance?","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kamath"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01257"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6846"},{"key":"ref42","article-title":"Learning robust representations by projecting superficial statistics out","author":"Wang","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220082"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5876"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.2307\/2951620"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240577"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6024"},{"key":"ref48","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref49","first-page":"7092","article-title":"Universal invariant and equivariant graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Keriven"},{"issue":"9","key":"ref50","first-page":"12","article-title":"A reduction of a graph to a canonical form and an algebra arising during this reduction","volume":"2","author":"Leman","year":"1968","journal-title":"Nauchno-Technicheskaya Informatsiya"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1093\/pan\/mpr025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2015.1023805"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12268"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273600"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"ref56","first-page":"19705","article-title":"Counterfactual prediction for bundle treatment","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zou"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"issue":"5","key":"ref58","first-page":"1393","article-title":"Feature selection via dependence maximization","volume":"13","author":"Song","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref59","first-page":"6666","article-title":"Generative causal explanations for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref60","article-title":"Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.50"},{"key":"ref63","article-title":"RDKit: Open-source cheminformatics","author":"Landrum","year":"2006"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/molecules26113125"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref67","article-title":"RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling","author":"Landrum","year":"2013"},{"issue":"9","key":"ref68","first-page":"2539","article-title":"Weisfeiler-Lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref69","first-page":"488","article-title":"Efficient graphlet kernels for large graph comparison","volume-title":"Proc. 12th Int. Conf. Artif. Intell. Statist.","author":"Shervashidze"},{"key":"ref70","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref72","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref73","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/81479"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3408317"},{"key":"ref76","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10345401\/10268633.pdf?arnumber=10268633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T01:18:06Z","timestamp":1703035086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10268633\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":76,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3321097","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}