{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T03:08:11Z","timestamp":1784603291158,"version":"3.55.0"},"reference-count":170,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["2023YFF1205001"],"award-info":[{"award-number":["2023YFF1205001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222209"],"award-info":[{"award-number":["62222209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","award":["BNR2023TD03006"],"award-info":[{"award-number":["BNR2023TD03006"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Key Lab of Networked Multimedia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3593897","type":"journal-article","created":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T18:31:16Z","timestamp":1753986676000},"page":"10490-10512","source":"Crossref","is-referenced-by-count":26,"title":["Out-of-Distribution Generalization on Graphs: A Survey"],"prefix":"10.1109","volume":"47","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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220077"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2017.2754499"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref5","article-title":"A meta-transfer objective for learning to disentangle causal mechanisms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bengio","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3193725"},{"key":"ref7","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/643"},{"key":"ref9","first-page":"2114","article-title":"Towards a unified framework for fair and stable graph representation learning","volume-title":"Proc. 37th Conf. Uncertainty Artif. Intell.","volume":"161","author":"Agarwal","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abbf9a"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16616"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3016780"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02353-5"},{"key":"ref15","article-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/628"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3575637.3575646"},{"key":"ref19","article-title":"Graph data augmentation for graph machine learning: A survey","author":"Zhao","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3170559"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3201243"},{"key":"ref23","article-title":"A Survey of adversarial learning on graphs","author":"Chen","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17315"},{"key":"ref25","first-page":"19010","article-title":"Metropolis-hastings data augmentation for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Park","year":"2021"},{"key":"ref26","first-page":"11815","article-title":"Knowledge distillation improves graph structure augmentation for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2022"},{"key":"ref27","first-page":"22092","article-title":"Graph random neural networks for semi-supervised learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00016"},{"key":"ref29","first-page":"14054","article-title":"Local augmentation for graph neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"162","author":"Liu","year":"2022"},{"key":"ref30","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539347"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01118"},{"key":"ref33","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","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645322"},{"key":"ref35","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref36","first-page":"4212","article-title":"Disentangled graph convolutional networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Ma","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5929"},{"key":"ref38","first-page":"20286","article-title":"Factorizable graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2020"},{"key":"ref39","first-page":"24934","article-title":"Debiasing graph neural networks via learning disentangled causal substructure","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan","year":"2022"},{"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. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3206875"},{"key":"ref43","first-page":"28890","article-title":"Disentangled graph self-supervised learning for out-of-distribution generalization","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Li","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321097"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3141260"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539366"},{"key":"ref47","article-title":"Deconfounding to explanation evaluation in graph neural networks","author":"Wu","year":"2022"},{"key":"ref48","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","year":"2022"},{"key":"ref49","first-page":"56860","article-title":"Empowering graph invariance learning with deep spurious infomax","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Yao","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_26"},{"key":"ref51","first-page":"27846","article-title":"Graph structure extrapolation for out-of-distribution generalization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645604"},{"key":"ref53","first-page":"837-851","article-title":"Size-invariant graph representations for graph classification extrapolations","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Bevilacqua","year":"2021"},{"key":"ref54","first-page":"20257","article-title":"OOD link prediction generalization capabilities of message-passing GNNs in larger test graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou","year":"2022"},{"key":"ref55","first-page":"26911","article-title":"Learning from counterfactual links for link prediction","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Zhao","year":"2022"},{"key":"ref56","first-page":"6666","article-title":"Generative causal explanations for graph neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Lin","year":"2021"},{"key":"ref57","first-page":"6666-6679","article-title":"Learning invariant graph representations under distribution shifts","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"139","author":"Li","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645332"},{"key":"ref59","article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2022"},{"key":"ref60","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Miao","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709203"},{"key":"ref62","article-title":"Disentangling invariant subgraph via variance contrastive estimation under distribution shifts","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li","year":"2025"},{"key":"ref63","article-title":"Handling distribution shifts on graphs: An invariance perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3604427"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599355"},{"key":"ref66","first-page":"9358","article-title":"Graphmetro: Mitigating complex graph distribution shifts via mixture of aligned experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu","year":"2024"},{"key":"ref67","first-page":"6074","article-title":"Dynamic graph neural networks under spatio-temporal distribution shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2022"},{"key":"ref68","first-page":"6619","article-title":"Spectral invariant learning for dynamic graphs under distribution shifts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2023"},{"key":"ref69","first-page":"49715","article-title":"Environment-aware dynamic graph learning for out-of-distribution generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan","year":"2023"},{"key":"ref70","first-page":"27965","article-title":"Shift-robust GNNs: Overcoming the limitations of localized graph training data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu","year":"2021"},{"key":"ref71","first-page":"31871","article-title":"SizeShiftReg: A regularization method for improving size-generalization in graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buffelli","year":"2022"},{"key":"ref72","first-page":"49","article-title":"Stable prediction on graphs with agnostic distribution shift","volume":"218","author":"Zhang","year":"2023","journal-title":"Proc. KDD\u201923 Workshop Causal Discovery, Prediction Decis."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/icdm.2019.00075"},{"key":"ref74","article-title":"Distributionally robust semi-supervised learning over graphs","author":"Sadeghi","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2019.2957786"},{"key":"ref76","article-title":"CAP: Co-adversarial perturbation on weights and features for improving generalization of graph neural networks","author":"Xue","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26239"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121671"},{"key":"ref79","article-title":"Strategies for pre-training graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2020"},{"key":"ref80","first-page":"11975","article-title":"From local structures to size generalization in graph neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Yehudai","year":"2021"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512172"},{"key":"ref82","first-page":"13052-13065","article-title":"Let invariant rationale discovery inspire graph contrastive learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"162","author":"Li","year":"2022"},{"key":"ref83","article-title":"Graphtta: Test time adaptation on graph neural networks","author":"Chen","year":"2022","journal-title":"Proc. Int. Conf. Mach. Learn., Workshop Princ. Distrib. Shift"},{"key":"ref84","article-title":"Test-time training for graph neural networks","author":"Wang","year":"2022"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3649507"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178128"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3370978"},{"key":"ref88","article-title":"Out-of-distribution generalization in time series: A survey","author":"Wu","year":"2025"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.soc.27.1.415"},{"key":"ref91","article-title":"Adversarial training for free!","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shafahi","year":"2019"},{"key":"ref92","article-title":"A closer look at distribution shifts and out-of-distribution generalization on graphs","volume-title":"Proc. NeurIPS 2021 Workshop Distrib. Shifts, Connecting Methods Appl.","author":"Ding","year":"2021"},{"key":"ref93","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"97","author":"Verma","year":"2019"},{"key":"ref94","article-title":"How does mixup help with robustness and generalization?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2021"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5822"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17203"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449796"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26412-2_32"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25941"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403063"},{"key":"ref101","first-page":"8230","article-title":"G-mixup: Graph data augmentation for graph classification","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Han","year":"2022"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3393109"},{"key":"ref103","article-title":"The role of disentanglement in generalisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Montero","year":"2020"},{"key":"ref104","article-title":"On the transfer of disentangled representations in realistic settings","author":"Dittadi","year":"2021","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref105","first-page":"585","article-title":"A Kernel statistical test of independence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gretton","year":"2007"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3031549"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2021.3058954"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220082"},{"key":"ref110","first-page":"1177","article-title":"Random features for large-scale Kernel machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rahimi","year":"2007"},{"key":"ref111","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2019"},{"key":"ref112","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying","year":"2018"},{"key":"ref113","volume-title":"Causal Inference in Statistics: A Primer","author":"Glymour","year":"2016"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/3501714.3501733"},{"key":"ref115","volume-title":"The Book of Why: The New Science of Cause and Effect","author":"Pearl","year":"2019"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.2307\/1912791.1969"},{"key":"ref117","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref118","first-page":"1448","article-title":"Invariant rationalization","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Chang","year":"2020"},{"key":"ref119","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","year":"2021"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/itw.2015.7133169"},{"key":"ref121","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref122","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"37","author":"Long","year":"2015"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.01.025"},{"key":"ref124","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Wu","year":"2019"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262170055.003.0008"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref127","article-title":"Distributionally robust optimization: A review","author":"Rahimian","year":"2019"},{"key":"ref128","first-page":"6450","article-title":"Domain generalization via model-agnostic learning of semantic features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Dou","year":"2019"},{"key":"ref129","first-page":"7313","article-title":"Domain generalization using causal matching","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Mahajan","year":"2021"},{"key":"ref130","first-page":"26484","article-title":"Correct-n-contrast: A contrastive approach for improving robustness to spurious correlations","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Zhang","year":"2022"},{"key":"ref131","first-page":"10871","article-title":"When does self-supervision help graph convolutional networks?","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"119","author":"You","year":"2020"},{"key":"ref132","article-title":"How neural networks extrapolate: From feedforward to graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2021"},{"key":"ref133","article-title":"Understanding attention and generalization in graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Knyazev","year":"2019"},{"key":"ref134","first-page":"2059","article-title":"GOOD: A graph out-of-distribution benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst Datasets Benchmarks Track","author":"Gui","year":"2022"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"ref136","article-title":"Drugood: Out-of-distribution (OOD) dataset curator and benchmark for ai-aided drug discovery","author":"Ji","year":"2022"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1093\/comnet\/cnab014"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.08.010"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21852-6_3"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330956"},{"key":"ref142","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"Bousquet","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref143","first-page":"3419","article-title":"Generalization and representational limits of graph neural networks","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Garg","year":"2020"},{"key":"ref144","article-title":"Generalization bounds for graph convolutional neural networks via rademacher complexity","author":"Lv","year":"2021"},{"key":"ref145","article-title":"A PAC-Bayesian approach to generalization bounds for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liao","year":"2021"},{"key":"ref146","first-page":"1048","article-title":"Subgroup generalization and fairness of graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.,","volume":"34","author":"Ma","year":"2021"},{"key":"ref147","first-page":"5723","article-title":"Graph neural tangent kernel: Fusing graph neural networks with graph kernels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du","year":"2019"},{"key":"ref148","first-page":"11268-11277","article-title":"Fast learning of graph neural networks with guaranteed generalizability: One-hidden-layer case","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Zhang","year":"2020"},{"key":"ref149","first-page":"684","article-title":"Graph convolution for semi-supervised classification: Improved linear separability and out-of-distribution generalization","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Baranwal","year":"2021"},{"key":"ref150","first-page":"4805","article-title":"Generalization analysis of message passing neural networks on large random graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Maskey","year":"2022"},{"key":"ref151","article-title":"Invariant graph learning meets information bottleneck for out-of-distribution generalization","author":"Mao","year":"2025","journal-title":"Front. Comput. Sci."},{"key":"ref152","first-page":"9244","article-title":"Gnnexplainer: Generating explanations for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying","year":"2019"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gky1075"},{"key":"ref157","article-title":"Neural execution of graph algorithms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107","year":"2020"},{"key":"ref158","article-title":"Learning to pool in graph neural networks for extrapolation","author":"Ko","year":"2021"},{"key":"ref159","article-title":"Customized graph neural networks","author":"Wang","year":"2020"},{"key":"ref160","first-page":"18083","article-title":"Graph neural architecture search under distribution shifts","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Qin","year":"2022"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn52387.2021.9533412"},{"key":"ref162","first-page":"59975","article-title":"Disentangled continual graph neural architecture search with invariant modular supernet","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Zhang","year":"2024"},{"key":"ref163","article-title":"Empowering graph representation learning with test-time graph transformation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin","year":"2023"},{"key":"ref164","article-title":"Online GNN evaluation under test-time graph distribution shifts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zheng","year":"2024"},{"key":"ref165","article-title":"Reliable graph neural networks for drug discovery under distributional shift","volume-title":"Proc. NeurIPS Workshop Distrib. Shifts, Connecting Methods Appl.","author":"Han","year":"2021"},{"key":"ref166","first-page":"12964","article-title":"Learning substructure invariance for out-of-distribution molecular representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2022"},{"key":"ref167","article-title":"Evaluating logical generalization in graph neural networks","volume-title":"Proc. 4th Lifelong Mach. Learn. Workshop","author":"Sinha","year":"2020"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20521"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-023-01012-9"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113640"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11106188.pdf?arnumber=11106188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:21Z","timestamp":1759772241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11106188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":170,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3593897","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":[[2025,11]]}}}