{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:09:35Z","timestamp":1780765775260,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFF0903300"],"award-info":[{"award-number":["2022YFF0903300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106266"],"award-info":[{"award-number":["62106266"]}],"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":["U22B2048"],"award-info":[{"award-number":["U22B2048"]}],"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":["62206292"],"award-info":[{"award-number":["62206292"]}],"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":["62206293"],"award-info":[{"award-number":["62206293"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3508766","type":"journal-article","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T18:53:07Z","timestamp":1732819987000},"page":"1627-1643","source":"Crossref","is-referenced-by-count":7,"title":["IBCS: Learning Information Bottleneck-Constrained Denoised Causal Subgraph for Graph Classification"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4649-0167","authenticated-orcid":false,"given":"Ruiwen","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9333-8200","authenticated-orcid":false,"given":"Yongqiang","family":"Tang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanghao","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0752-941X","authenticated-orcid":false,"given":"Wensheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref2","first-page":"2713","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref3","first-page":"9104","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403237"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00047"},{"key":"ref7","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miao"},{"key":"ref8","first-page":"4849","article-title":"Multi-objective molecule generation using interpretable substructures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref9","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krueger"},{"key":"ref10","first-page":"1","article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539366"},{"key":"ref12","first-page":"24934","article-title":"Debiasing graph neural networks via learning disentangled causal substructure","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref13","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":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3112205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01879"},{"key":"ref18","first-page":"76737","article-title":"Interpretable prototype-based graph information bottleneck","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Seo"},{"key":"ref19","first-page":"1","article-title":"Interpretable geometric deep learning via learnable randomness injection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miao"},{"key":"ref20","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref21","first-page":"9244","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"issue":"2","key":"ref22","first-page":"35","article-title":"A survey on explainability of graph neural networks","volume":"46","author":"Kakkad","year":"2023","journal-title":"Bull. IEEE Comput. Soc. Tech. Committee Data Eng."},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20703"},{"key":"ref25","article-title":"Invariant graph learning meets information bottleneck for out-of-distribution generalization","author":"Mao","year":"2024"},{"key":"ref26","first-page":"334","article-title":"Capsule graph neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xinyi"},{"key":"ref27","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref28","first-page":"1","article-title":"Sign and basis invariant networks for spectral graph representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lim"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3154319"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3202158"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3392782"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3062794"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203703"},{"key":"ref35","article-title":"Learning graph representations with recurrent neural network autoencoders","author":"Taheri","year":"2018","journal-title":"KDD Deep Learn. Day"},{"key":"ref36","article-title":"Graph capsule convolutional neural networks","author":"Verma","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327389"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5997"},{"key":"ref39","first-page":"2083","article-title":"Graph U-nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref41","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref42","first-page":"18109","article-title":"Unleashing the power of graph data augmentation on covariate distribution shift","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sui"},{"key":"ref43","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv:physics\/0004057"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321097"},{"key":"ref45","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":"ref46","volume-title":"Models, Reasoning and Inference","volume":"19","author":"Pearl","year":"2000"},{"key":"ref47","volume-title":"Causal Inference in Statistics: A Primer","author":"Pearl","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1037\/a0036434"},{"key":"ref49","first-page":"36839","article-title":"Boosting graph contrastive learning via graph contrastive saliency","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref50","first-page":"37511","article-title":"Rethinking explaining graph neural networks via non-parametric subgraph matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref51","article-title":"Mine: Mutual information neural estimation","author":"Belghazi","year":"2018"},{"key":"ref52","first-page":"9153","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235931"},{"key":"ref54","first-page":"5171","article-title":"On variational bounds of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Poole"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref56","first-page":"4204","article-title":"Understanding attention and generalization in graph neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Knyazev"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref60","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":"ref61","article-title":"Tudataset: A. collection of benchmark datasets for learning with graphs","author":"Morris","year":"2020"},{"key":"ref62","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01118"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28700"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10771715.pdf?arnumber=10771715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:39:27Z","timestamp":1738820367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10771715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3508766","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":[[2025,3]]}}}