{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:32:00Z","timestamp":1782174720237,"version":"3.54.5"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0111501"],"award-info":[{"award-number":["2021ZD0111501"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014717","name":"Youth Science Fund Project","doi-asserted-by":"publisher","award":["62122022"],"award-info":[{"award-number":["62122022"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20233"],"award-info":[{"award-number":["U24A20233"]}],"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":["62206064"],"award-info":[{"award-number":["62206064"]}],"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":["62206061"],"award-info":[{"award-number":["62206061"]}],"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":["62476163"],"award-info":[{"award-number":["62476163"]}],"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":["62406078"],"award-info":[{"award-number":["62406078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011901"],"award-info":[{"award-number":["2024A1515011901"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A04J1700"],"award-info":[{"award-number":["2023A04J1700"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515120020"],"award-info":[{"award-number":["2023B1515120020"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["2229881"],"award-info":[{"award-number":["2229881"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL159805"],"award-info":[{"award-number":["R01HL159805"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"KDDI Research Inc."},{"name":"Salesforce Inc"},{"DOI":"10.13039\/100006112","name":"Microsoft Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006112","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpami.2025.3598461","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:34:24Z","timestamp":1755106464000},"page":"11614-11631","source":"Crossref","is-referenced-by-count":3,"title":["Identifying Semantic Component for Robust Molecular Property Prediction"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3964-3789","authenticated-orcid":false,"given":"Zijian","family":"Li","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunhong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8972-167X","authenticated-orcid":false,"given":"Ruichu","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9879-4758","authenticated-orcid":false,"given":"Yuguang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9731-1504","authenticated-orcid":false,"given":"Zhifeng","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-5378","authenticated-orcid":false,"given":"Guangyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0738-9958","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00418-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-019-0124-0"},{"key":"ref4","article-title":"Pre-training graph neural networks for molecular representations: Retrospect and prospect","volume-title":"Proc. 2nd AI Sci. Workshop","author":"Xia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-019-0024-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25970"},{"key":"ref7","first-page":"7236","article-title":"TANKBind: Trigonometry-aware neural networks for drug-protein binding structure prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26679"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599559"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0337-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccr.2008.05.014"},{"key":"ref12","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref13","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011052"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20377"},{"key":"ref16","article-title":"Strategies for pre-training graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref17","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rong"},{"key":"ref18","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3193725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3593897"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321097"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00110"},{"key":"ref24","article-title":"Variational graph auto-encoders","author":"Kipf","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00140-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10463-023-00884-4"},{"key":"ref27","first-page":"12768","article-title":"Ice-BeeM: Identifiable conditional energy-based deep models based on nonlinear ICA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khemakhem"},{"key":"ref28","article-title":"On the identifiability of nonlinear ICA with unconditional priors","volume-title":"Proc. Workshop Elements Reasoning: Objects Struct. Causality","author":"Zheng"},{"key":"ref29","first-page":"2","article-title":"Analyse des liaisons de probabilit\u00e9","volume-title":"Proc. Int. Statist. Conf.","author":"Darmois"},{"key":"ref30","article-title":"Discovering invariant rationales for graph neural networks","author":"Wu","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c01224"},{"key":"ref33","first-page":"15870","article-title":"Motif-based graph self-supervised learning for molecular property prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref34","first-page":"18872","article-title":"Exploring chemical space with score-based out-of-distribution generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref35","first-page":"20479","article-title":"3D infomax improves GNNs for molecular property prediction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"St\u00e4rk"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539426"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.11.009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"ref39","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab195"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411981"},{"key":"ref43","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00110"},{"key":"ref45","article-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref47","first-page":"34940","article-title":"Multi-instance causal representation learning for instance label prediction and out-of-distribution generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.338"},{"key":"ref49","first-page":"30277","article-title":"GraphDE: A generative framework for debiased learning and out-of-distribution detection on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref50","first-page":"12827","article-title":"Uncertainty aware semi-supervised learning on graph data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539366"},{"key":"ref53","first-page":"12096","article-title":"Does GNN pretraining help molecular representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3193725"},{"key":"ref55","first-page":"18109","article-title":"Unleashing the power of graph data augmentation on covariate distribution shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sui"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599437"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3112205"},{"key":"ref59","article-title":"Graph information bottleneck for subgraph recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01879"},{"key":"ref61","first-page":"6666","article-title":"Generative causal explanations for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref62","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref64","article-title":"Variational inference of disentangled latent concepts from unlabeled observations","author":"Kumar","year":"2017"},{"key":"ref65","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Locatello"},{"key":"ref66","article-title":"Disentangling factors of variation using few labels","author":"Locatello","year":"2019"},{"key":"ref67","first-page":"10401","article-title":"On disentangled representations learned from correlated data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tr\u00e4uble"},{"issue":"2","key":"ref68","first-page":"205","article-title":"Independent component analysis","volume":"11","author":"Hyvarinen","year":"2002","journal-title":"Stud. Informat. Control"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2011.0534"},{"key":"ref70","first-page":"2455","article-title":"Minimal nonlinear distortion principle for nonlinear independent component analysis","volume":"9","author":"Zhang","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74494-8_38"},{"key":"ref72","article-title":"Multi-domain image generation and translation with identifiability guarantees","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Xie"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(94)90029-9"},{"key":"ref74","first-page":"3765","article-title":"Unsupervised feature extraction by time-contrastive learning and nonlinear ICA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hyvarinen"},{"key":"ref75","first-page":"460","article-title":"Nonlinear ICA of temporally dependent stationary sources","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hyvarinen"},{"key":"ref76","first-page":"859","article-title":"Nonlinear ICA using auxiliary variables and generalized contrastive learning","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Hyvarinen"},{"key":"ref77","first-page":"2207","article-title":"Variational autoencoders and nonlinear ICA: A unifying framework","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Khemakhem"},{"key":"ref78","first-page":"1624","article-title":"Disentangling identifiable features from noisy data with structured nonlinear ICA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"H\u00e4lv\u00e4"},{"key":"ref79","first-page":"939","article-title":"Hidden Markov nonlinear ICA: Unsupervised learning from nonstationary time series","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"H\u00e4lv\u00e4"},{"key":"ref80","first-page":"11455","article-title":"Partial disentanglement for domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kong"},{"key":"ref81","article-title":"Temporally disentangled representation learning","author":"Yao","year":"2022"},{"key":"ref82","article-title":"Learning temporally causal latent processes from general temporal data","author":"Yao","year":"2021"},{"key":"ref83","article-title":"Subspace identification for multi-source domain adaptation","author":"Li","year":"2023"},{"key":"ref84","first-page":"16451","article-title":"Self-supervised learning with data augmentations provably isolates content from style","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Von K\u00fcgelgen"},{"key":"ref85","first-page":"12979","article-title":"Contrastive learning inverts the data generating process","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zimmermann"},{"key":"ref86","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref87","first-page":"12311","article-title":"Invertible gaussian reparameterization: Revisiting the gumbel-softmax","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Potapczynski"},{"key":"ref88","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":"ref89","first-page":"2059","article-title":"GOOD: A graph out-of-distribution benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gui"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref91","article-title":"RDKit: Open-source cheminformatics software","author":"Landrum","year":"2016"},{"key":"ref92","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref93","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velickovic","year":"2018"},{"key":"ref94","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref95","article-title":"How powerful are graph neural networks","author":"Xu","year":"2018"},{"key":"ref96","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref97","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/392"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00959"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-023-00691-2"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1038\/s42004-023-00857-x"},{"key":"ref102","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":"ref103","article-title":"Joint learning of label and environment causal independence for graph out-of-distribution generalization","author":"Gui","year":"2023"},{"key":"ref104","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Miao"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpj.2014.06.024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11230086\/11123751.pdf?arnumber=11123751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:16Z","timestamp":1762455196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11123751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":105,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3598461","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":[[2025,12]]}}}