{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T23:13:07Z","timestamp":1774048387086,"version":"3.50.1"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62225202"],"award-info":[{"award-number":["62225202"]}],"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":["62302023"],"award-info":[{"award-number":["62302023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["POSE-2346158"],"award-info":[{"award-number":["POSE-2346158"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3631584","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:27:49Z","timestamp":1762885669000},"page":"2714-2730","source":"Crossref","is-referenced-by-count":1,"title":["Evolving Graph Learning for Out-of-Distribution Generalization in Non-Stationary Environments"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1930-3848","authenticated-orcid":false,"given":"Qingyun","family":"Sun","sequence":"first","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Jiayi","family":"Luo","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Haonan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Xingcheng","family":"Fu","sequence":"additional","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0458-5977","authenticated-orcid":false,"given":"Hao","family":"Peng","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5152-0055","authenticated-orcid":false,"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Advanced Innovation Center for Big Data and Brain Computing, School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161804"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-016-0325-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3118815"},{"key":"ref5","article-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"ref6","first-page":"27965","article-title":"Shift-robust gnns: Overcoming the limitations of localized graph training data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3193725"},{"key":"ref9","first-page":"22131","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":"ref10","first-page":"2059","article-title":"Good: A graph out-of-distribution benchmark","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gui"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3321097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS057"},{"key":"ref13","first-page":"39","article-title":"Causal inference","volume-title":"Proc. Causality: Objectives Assessment","author":"Pearl"},{"key":"ref14","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2018"},{"key":"ref15","article-title":"Woods: Benchmarks for out-of-distribution generalization in time series tasks","author":"Gagnon-Audet","year":"2022"},{"key":"ref16","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref17","article-title":"The risks of invariant risk minimization","author":"Rosenfeld","year":"2020"},{"key":"ref18","article-title":"Discovering invariant rationales for graph neural networks","author":"Wu","year":"2022"},{"key":"ref19","first-page":"1448","article-title":"Invariant rationalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref20","first-page":"145","article-title":"Invariant risk minimization games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ahuja"},{"key":"ref21","article-title":"Representation learning via invariant causal mechanisms","author":"Mitrovic","year":"2020"},{"key":"ref22","volume-title":"Elements of causal inference: foundations and learning algorithms","author":"Peters","year":"2017"},{"key":"ref23","first-page":"30277","article-title":"Graphde: A generative framework for debiased learning and out-of-distribution detection on graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref24","first-page":"6074","article-title":"Dynamic graph neural networks under spatio-temporal distribution shift","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262017091.001.0001"},{"key":"ref26","article-title":"Hop Sampling: A simple regularized graph learning for non-stationary environments","volume-title":"Proc. SIGKDD 2020 Workshop Mining Learn. Graphs","author":"Park"},{"key":"ref27","first-page":"49715","article-title":"Environment-aware dynamic graph learning for out-of-distribution generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04167-0_33"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371845"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11257"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220054"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109766"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3233\/faia200270"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"ref36","first-page":"4212","article-title":"Disentangled graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5929"},{"key":"ref38","first-page":"24934","article-title":"Debiasing graph neural networks via learning disentangled causal substructure","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref39","first-page":"20286","article-title":"Factorizable graph convolutional networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403221"},{"key":"ref41","first-page":"21872","article-title":"Disentangled contrastive learning on graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3206875"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3141260"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539366"},{"key":"ref45","first-page":"26911","article-title":"Learning from counterfactual links for link prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref46","first-page":"6666","article-title":"Generative causal explanations for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref47","first-page":"22092","article-title":"Graph random neural networks for semi-supervised learning on graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00016"},{"key":"ref49","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"You"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref51","article-title":"Finding diverse and predictable subgraphs for graph domain generalization","author":"Yu","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17203"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449796"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403063"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17315"},{"key":"ref57","first-page":"19010","article-title":"Metropolis-hastings data augmentation for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref58","first-page":"11815","article-title":"Knowledge distillation improves graph structure augmentation for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref59","article-title":"Adversarial causal augmentation for graph covariate shift","author":"Sui","year":"2022"},{"key":"ref60","first-page":"14054","article-title":"Local augmentation for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref61","article-title":"Intrusion-free graph mixup","author":"Guo","year":"2022"},{"key":"ref62","first-page":"8230","article-title":"G-mixup: Graph data augmentation for graph classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref63","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miao"},{"key":"ref64","article-title":"Handling distribution shifts on graphs: An invariance perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref65","first-page":"11828","article-title":"Learning invariant graph representations for out-of-distribution generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref66","first-page":"31871","article-title":"SizeShiftReg: A regularization method for improving size-generalization in graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Buffelli"},{"key":"ref67","first-page":"13052","article-title":"Let invariant rationale discovery inspire graph contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3604427"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599355"},{"key":"ref70","article-title":"Deconfounding to explanation evaluation in graph neural networks","author":"Wu","year":"2022"},{"key":"ref71","first-page":"20257","article-title":"OOD link prediction generalization capabilities of message-passing GNNs in larger test graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref72","first-page":"837","article-title":"Size-invariant graph representations for graph classification extrapolations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bevilacqua"},{"key":"ref73","first-page":"3945","article-title":"Joint learning of label and environment causal independence for graph out-of-distribution generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gui"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3644392"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645604"},{"key":"ref76","first-page":"6619","article-title":"Spectral invariant learning for dynamic graphs under distribution shifts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2239"},{"key":"ref78","first-page":"104965","article-title":"Pure: Prompt evolution with graph ode for out-of-distribution fluid dynamics modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709273"},{"issue":"1","key":"ref80","first-page":"1309","article-title":"Invariant models for causal transfer learning","volume":"19","author":"Rojas-Carulla","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref81","first-page":"2189","article-title":"Environment inference for invariant learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Creager"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00116"},{"key":"ref83","first-page":"7523","article-title":"On learning invariant representations for domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1214\/20-STS797"},{"key":"ref85","first-page":"2839","article-title":"Domain adaptation with conditional transferable components","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gong"},{"key":"ref86","article-title":"Certifying some distributional robustness with principled adversarial training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sinha"},{"key":"ref87","first-page":"3012","volume-title":"Proc. Int. Conf. Data Eng.","author":"Chen"},{"key":"ref88","first-page":"20498","article-title":"Autost: Towards the universal modeling of spatio-temporal sequences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref89","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2555904"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/BF02418571"},{"key":"ref94","first-page":"17628","article-title":"An information-theoretic approach to distribution shifts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Federici"},{"key":"ref95","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krueger"},{"key":"ref96","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"Sagawa","year":"2019"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339730"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330895"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/0378-8733(83)90021-7"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01118"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/11372200\/11240237-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11240237.pdf?arnumber=11240237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:38Z","timestamp":1770671138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":100,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3631584","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":[[2026,3]]}}}