{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T20:21:08Z","timestamp":1778617268935,"version":"3.51.4"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["92370201"],"award-info":[{"award-number":["92370201"]}],"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":["62222607"],"award-info":[{"award-number":["62222607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018735","name":"Ant Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3654544","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:49:41Z","timestamp":1768510181000},"page":"6139-6155","source":"Crossref","is-referenced-by-count":0,"title":["Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-7679","authenticated-orcid":false,"given":"Junchi","family":"Yan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2173-4840","authenticated-orcid":false,"given":"Fangyu","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1048-5443","authenticated-orcid":false,"given":"Jiawei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8124-2899","authenticated-orcid":false,"given":"Zhaoping","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539415"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/643"},{"key":"ref3","first-page":"1","article-title":"How powerful are graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref4","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539366"},{"key":"ref6","first-page":"12964","article-title":"Learning substructure invariance for out-of-distribution molecular representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0859"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2310"},{"key":"ref9","first-page":"1","article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref10","first-page":"4212","article-title":"Disentangled graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref11","first-page":"1","article-title":"Handling distribution shifts on graphs: An invariance perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref12","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastsgood IC attention mechanism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miao"},{"key":"ref13","first-page":"22131","article-title":"Learning causally invariant representations for out-of-distribution generalization on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nchem.1607"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref17","first-page":"1","article-title":"Graph information bottleneck for subgraph recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref18","first-page":"679","article-title":"Compact representations of separable graphs","volume-title":"Proc. Annu. ACM-SIAM Symp. Discrete Algorithms","author":"Blandford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461884"},{"key":"ref20","first-page":"1","article-title":"Towards one-shot neural combinatorial solvers: Theoretical and empirical notes on the cardinality-constrained case","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703591"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3785475"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref25","first-page":"1","article-title":"Rethinking invariant graph representation learning without environment partitions","volume-title":"Proc. ICLR 2023 Workshop DG Poster","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679710"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28700"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34065"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35412"},{"key":"ref31","first-page":"71486","article-title":"Does invariant graph learning via environment augmentation learn invariance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1808"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.112551"},{"key":"ref34","first-page":"6413","article-title":"How interpretable are interpretable graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref35","first-page":"56860","article-title":"Empowering graph invariance learning with deep spurious infomax","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref36","first-page":"18365","article-title":"Learning graph invariance by harnessing spuriosity","volume-title":"Proc. Int. Conf. Representation Learn.","author":"Yao"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-58412-1"},{"key":"ref38","first-page":"6659","article-title":"Erdos goes neural: An unsupervised learning framework for combinatorial optimization on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karalias"},{"key":"ref39","first-page":"20520","article-title":"Differentiable top-k operator with optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3489030"},{"key":"ref41","first-page":"1","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref42","first-page":"2292","article-title":"Sinkhorn Distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref43","article-title":"Invariance principle meets out-of-distribution generalization on graphs","author":"Chen","year":"2022"},{"key":"ref44","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Corso"},{"key":"ref45","first-page":"831","article-title":"Principles of risk minimization for learning theory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vapnik"},{"key":"ref46","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref47","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krueger"},{"key":"ref48","first-page":"2189","article-title":"Environment inference for invariant learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Creager"},{"key":"ref49","first-page":"3438","article-title":"Invariance principle meets information bottleneck for out-of-distribution generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ahuja"},{"key":"ref50","first-page":"26484","article-title":"Correct-n-contrast: A contrastive approach for improving robustness to spurious correlations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5997"},{"key":"ref52","first-page":"4204","article-title":"Understanding attention and generalization in graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Knyazev"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3204236"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref56","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25970"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2009"},{"key":"ref60","article-title":"TUDataset: A collection of benchmark datasets for learning with graphs","author":"Morris","year":"2020"},{"key":"ref61","first-page":"837","article-title":"Size-invariant graph representations for graph classification extrapolations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bevilacqua"},{"key":"ref62","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref63","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref64","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref65","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1093\/comnet\/cnab014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2011.12.021"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"ref69","first-page":"9244","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref70","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref71","first-page":"1","article-title":"Interpreting graph neural networks for NLP with differentiable edge masking","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schlichtkrull"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/694"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3078053"},{"key":"ref74","first-page":"1","article-title":"Optimal flow transport and its entropic regularization: A GPU-friendly matrix iterative algorithm for flow balance satisfaction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi"},{"key":"ref75","first-page":"39903","article-title":"Towards quantum machine learning for constrained combinatorial optimization: A quantum QAP solver","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ye"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0442"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11355693.pdf?arnumber=11355693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:48:50Z","timestamp":1778615330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11355693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":76,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3654544","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":[[2026,6]]}}}