{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T01:22:29Z","timestamp":1776388949274,"version":"3.51.2"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0106300"],"award-info":[{"award-number":["2020AAA0106300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250008"],"award-info":[{"award-number":["62250008"]}],"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":["62102222"],"award-info":[{"award-number":["62102222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2023,7,1]]},"DOI":"10.1109\/tkde.2022.3193725","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T20:08:04Z","timestamp":1658779684000},"page":"7328-7340","source":"Crossref","is-referenced-by-count":87,"title":["OOD-GNN: Out-of-Distribution Generalized Graph Neural Network"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3544-5563","authenticated-orcid":false,"given":"Haoyang","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2451-843X","authenticated-orcid":false,"given":"Ziwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nrg1272"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511761942"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"ref5","article-title":"Semi-supervised classification with graph\n                        convolutional networks","volume-title":"Proc. Int. Conf.\n                        Learn. Representations","author":"Kipf"},{"key":"ref6","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref7","article-title":"How powerful are graph neural\n                        networks?","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Xu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01588-5"},{"key":"ref9","article-title":"Learning graph-level representation for drug\n                        discovery","author":"Li","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3008732"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3050571"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty294"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00559"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1098-1128(199601)16:1<3::AID-MED1>3.0.CO;2-6"},{"key":"ref15","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine\n                        learning on graphs","volume-title":"Proc. Adv. Neural\n                        Inf. Process. Syst.","author":"Hu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0070"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041924"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358156"},{"key":"ref19","first-page":"4202","article-title":"Understanding attention and generalization in graph\n                        neural networks","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Knyazev"},{"key":"ref20","first-page":"11975","article-title":"From local structures to size generalization in graph\n                        neural networks","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Yehudai"},{"key":"ref21","first-page":"837","article-title":"Size-invariant graph representations for graph\n                        classification extrapolations","volume-title":"Proc. Int.\n                        Conf. Mach. Learn.","author":"Bevilacqua"},{"key":"ref22","article-title":"How neural networks extrapolate: From feedforward to\n                        graph neural networks","volume-title":"Proc. Int. Conf.\n                        Learn. Representations","author":"Xu"},{"key":"ref23","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00335"},{"key":"ref25","first-page":"4334","article-title":"Learning to reweight examples for robust deep\n                        learning","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Ren"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220082"},{"key":"ref27","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution\n                        shifts","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Koh"},{"key":"ref28","article-title":"Random features for large-scale kernel\n                        machines","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","author":"Rahimi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref30","first-page":"3905","article-title":"Towards a unified analysis of random fourier\n                        features","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref33","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3090664"},{"key":"ref35","first-page":"1025","article-title":"Inductive representation learning on large\n                        graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf.\n                        Process. Syst.","author":"Hamilton"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3076772"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3074654"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3105544"},{"key":"ref41","article-title":"Out-of-distribution generalization on graphs: A\n                        survey","author":"Li","year":"2022"},{"key":"ref42","first-page":"4477","article-title":"Measuring abstract reasoning in neural\n                        networks","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Santoro"},{"key":"ref43","article-title":"Analysing mathematical reasoning abilities of neural\n                        models","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Saxton"},{"key":"ref44","article-title":"Neural execution of graph\n                    algorithms","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref45","article-title":"What graph neural networks cannot learn: Depth vs\n                        width","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Loukas"},{"key":"ref46","first-page":"3419","article-title":"Generalization and representational limits of graph\n                        neural networks","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Garg"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330956"},{"key":"ref48","article-title":"Reducing overfitting in deep networks by\n                        decorrelating representations","volume-title":"Proc. Int.\n                        Conf. Learn. Representations","author":"Cogswell"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/301"},{"key":"ref50","article-title":"Predicting with high correlation\n                        features","author":"Arpit","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/jaba.760"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2227680"},{"key":"ref53","article-title":"Regularizing CNNs with locally constrained\n                        decorrelations","author":"Rodr\u00edguez","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5876"},{"key":"ref56","article-title":"Removing the feature correlation effect of\n                        multiplicative noise","author":"Zhang","year":"2018"},{"key":"ref57","first-page":"528","article-title":"Learning de-biased representations with biased\n                        representations","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Bahng"},{"key":"ref58","first-page":"322","article-title":"DIVA: Domain invariant variational\n                        autoencoders","volume-title":"Proc. 3rd Conf. Med. Imag.\n                        Deep Learn.","author":"Ilse"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"ref60","first-page":"489","article-title":"Kernel measures of conditional\n                        dependence","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Fukumizu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1515\/jci-2018-0017"},{"key":"ref62","first-page":"20286","article-title":"Factorizable graph convolutional\n                        networks","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","author":"Yang"},{"key":"ref63","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph\n                        nets","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","author":"Corso"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3081010"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1515\/9781400841356.38"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM.2014.6921561"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2021.3103984"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240577"},{"key":"ref73","article-title":"Why stable learning works? A theory of covariate\n                        shift generalization","author":"Xu","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref75","first-page":"517","article-title":"Learning to decompose and disentangle representations\n                        for video prediction","volume-title":"Proc. Adv. Neural\n                        Inf. Process. Syst.","author":"Hsieh"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"ref77","first-page":"4212","article-title":"Disentangled graph convolutional\n                        networks","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Ma"},{"key":"ref78","article-title":"Understanding disentangling in\n                        \u03b2-vae","author":"Burgess","year":"2017","journal-title":"NeurIPS Workshop Learn.\n                        Disentangled Representations"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10144447\/09839432.pdf?arnumber=9839432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:58:00Z","timestamp":1725904680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9839432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":78,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3193725","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,1]]}}}