{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:56:03Z","timestamp":1769831763251,"version":"3.49.0"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"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\/501100007162","name":"Department of Science and Technology of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007225","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":["U24A20233"],"award-info":[{"award-number":["U24A20233"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2021ZD0111501"],"award-info":[{"award-number":["2021ZD0111501"]}],"id":[{"id":"10.13039\/501100013076","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"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1016\/j.neunet.2024.107044","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T22:51:57Z","timestamp":1734735117000},"page":"107044","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Unifying invariant and variant features for graph out-of-distribution via probability of necessity and sufficiency"],"prefix":"10.1016","volume":"184","author":[{"given":"Xuexin","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8972-167X","authenticated-orcid":false,"given":"Ruichu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaitao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengting","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2024.107044_b1","series-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"10.1016\/j.neunet.2024.107044_b2","unstructured":"Bai, Yingbin, Han, Zhongyi, Yang, Erkun, Yu, Jun, Han, Bo, Wang, Dadong, et al. (2023). Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping. In Thirty-seventh conference on neural information processing systems."},{"issue":"6","key":"10.1016\/j.neunet.2024.107044_b3","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1007\/s10992-021-09601-z","article-title":"Causal sufficiency and actual causation","volume":"50","author":"Beckers","year":"2021","journal-title":"Journal of Philosophical Logic"},{"key":"10.1016\/j.neunet.2024.107044_b4","unstructured":"Cai, Hengrui, Wang, Yixin, Jordan, Michael I., & Song, Rui (2023). On Learning Necessary and Sufficient Causal Graphs. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, & Sergey Levine (Eds.), Advances in neural information processing systems 36: annual conference on neural information processing systems 2023, NeurIPS 2023, New Orleans, La, USA, December 10 - 16, 2023."},{"key":"10.1016\/j.neunet.2024.107044_b5","series-title":"On the probability of necessity and sufficiency of explaining graph neural networks: A lower bound optimization approach","author":"Cai","year":"2022"},{"key":"10.1016\/j.neunet.2024.107044_b6","article-title":"Does invariant graph learning via environment augmentation learn invariance?","volume":"36","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b7","series-title":"Feature attribution with necessity and sufficiency via dual-stage perturbation test for causal explanation","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2024.107044_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.mser.2020.100595","article-title":"Polymer informatics: Current status and critical next steps","volume":"144","author":"Chen","year":"2021","journal-title":"Materials Science and Engineering Reports"},{"key":"10.1016\/j.neunet.2024.107044_b9","doi-asserted-by":"crossref","unstructured":"Chen, Jiaao, Shen, Dinghan, Chen, Weizhu, & Yang, Diyi (2021). Hiddencut: Simple data augmentation for natural language understanding with better generalizability. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing (volume 1: long papers) (pp. 4380\u20134390).","DOI":"10.18653\/v1\/2021.acl-long.338"},{"key":"10.1016\/j.neunet.2024.107044_b10","unstructured":"Chen, Yongqiang, Zhang, Yonggang, Bian, Yatao, Yang, Han, Kaili, MA, Xie, Binghui, et al. (2022a). Invariance principle meets out-of-distribution generalization on graphs. In ICML 2022: workshop on spurious correlations, invariance and stability."},{"key":"10.1016\/j.neunet.2024.107044_b11","first-page":"22131","article-title":"Learning causally invariant representations for out-of-distribution generalization on graphs","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2024.107044_b12","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1093\/lpr\/mgx012","article-title":"The probability of causation","volume":"16","author":"Dawid","year":"2017","journal-title":"Law, Probability and Risk"},{"key":"10.1016\/j.neunet.2024.107044_b13","series-title":"Advances in neural information processing systems 36: annual conference on neural information processing systems 2023, NeurIPS 2023, New Orleans, La, USA, December 10 - 16, 2023","article-title":"Spuriosity didn\u2019t kill the classifier: Using invariant predictions to harness spurious features","author":"Eastwood","year":"2023"},{"key":"10.1016\/j.neunet.2024.107044_b14","article-title":"Generalizing graph neural networks on out-of-distribution graphs","author":"Fan","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2024.107044_b15","doi-asserted-by":"crossref","unstructured":"Fang, Zheng, Zhang, Ziyun, Song, Guojie, Zhang, Yingxue, Li, Dong, Hao, Jianye, et al. (2022). Invariant Factor Graph Neural Networks. In 2022 IEEE international conference on data mining (pp. 933\u2013938). http:\/\/dx.doi.org\/10.1109\/ICDM54844.2022.00110.","DOI":"10.1109\/ICDM54844.2022.00110"},{"key":"10.1016\/j.neunet.2024.107044_b16","doi-asserted-by":"crossref","unstructured":"Galhotra, Sainyam, Pradhan, Romila, & Salimi, Babak (2021). Explaining black-box algorithms using probabilistic contrastive counterfactuals. In Proceedings of the 2021 international conference on management of data (pp. 577\u2013590).","DOI":"10.1145\/3448016.3458455"},{"key":"10.1016\/j.neunet.2024.107044_b17","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1023\/A:1009602825894","article-title":"An axiomatic characterization of causal counterfactuals","volume":"3","author":"Galles","year":"1998","journal-title":"Foundations of Science"},{"issue":"23","key":"10.1016\/j.neunet.2024.107044_b18","doi-asserted-by":"crossref","first-page":"4733","DOI":"10.1002\/sim.8331","article-title":"Quantifying degrees of necessity and of sufficiency in cause-effect relationships with dichotomous and survival outcomes","volume":"38","author":"Gleiss","year":"2019","journal-title":"Statistics in Medicine"},{"key":"10.1016\/j.neunet.2024.107044_b19","first-page":"2059","article-title":"Good: A graph out-of-distribution benchmark","volume":"35","author":"Gui","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b20","doi-asserted-by":"crossref","unstructured":"Guo, Zhichun, Yu, Wenhao, Zhang, Chuxu, Jiang, Meng, & Chawla, Nitesh V. (2020). GraSeq: graph and sequence fusion learning for molecular property prediction. In Proceedings of the 29th ACM international conference on information & knowledge management (pp. 435\u2013443).","DOI":"10.1145\/3340531.3411981"},{"key":"10.1016\/j.neunet.2024.107044_b21","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1613\/jair.648","article-title":"Axiomatizing causal reasoning","volume":"12","author":"Halpern","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.neunet.2024.107044_b22","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b23","series-title":"Causal inference","author":"Hern\u00e1n","year":"2010"},{"key":"10.1016\/j.neunet.2024.107044_b24","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b25","series-title":"5th international conference on learning representations, ICLR 2017, Toulon, France, April 24-26, 2017, conference track proceedings","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2017"},{"key":"10.1016\/j.neunet.2024.107044_b26","series-title":"5th international conference on learning representations, ICLR 2017, Toulon, France, April 24-26, 2017, conference track proceedings","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.neunet.2024.107044_b27","series-title":"International conference on machine learning","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (rex)","author":"Krueger","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2024.107044_b28","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1111\/j.1467-9469.2011.00730.x","article-title":"Statistical analysis of \u2018probabilities of causation\u2019using co-variate information","volume":"38","author":"Kuroki","year":"2011","journal-title":"Scandinavian Journal of Statistics"},{"key":"10.1016\/j.neunet.2024.107044_b29","article-title":"Domain-adversarial training of neural networks","author":"Lempitsky","year":"2016","journal-title":"The Journal"},{"key":"10.1016\/j.neunet.2024.107044_b30","unstructured":"Li, Zijian, Cai, Ruichu, Chen, Guangyi, Sun, Boyang, Hao, Zhifeng, & Zhang, Kun (2023). Subspace Identification for Multi-Source Domain Adaptation. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, & Sergey Levine (Eds.), Advances in neural information processing systems 36: annual conference on neural information processing systems 2023, NeurIPS 2023, New Orleans, La, USA, December 10 - 16, 2023."},{"key":"10.1016\/j.neunet.2024.107044_b31","doi-asserted-by":"crossref","unstructured":"Li, Ang, & Pearl, Judea (2019). Unit selection based on counterfactual logic. In Proceedings of the twenty-eighth international joint conference on artificial intelligence.","DOI":"10.24963\/ijcai.2019\/248"},{"key":"10.1016\/j.neunet.2024.107044_b32","doi-asserted-by":"crossref","unstructured":"Li, Ang, & Pearl, Judea (2022a). Bounds on causal effects and application to high dimensional data. In Proceedings of the AAAI conference on artificial intelligence, Vol. 36 (pp. 5773\u20135780).","DOI":"10.1609\/aaai.v36i5.20520"},{"key":"10.1016\/j.neunet.2024.107044_b33","doi-asserted-by":"crossref","unstructured":"Li, Ang, & Pearl, Judea (2022b). Unit selection with causal diagram. In Proceedings of the AAAI conference on artificial intelligence, Vol. 36 (pp. 5765\u20135772).","DOI":"10.1609\/aaai.v36i5.20519"},{"key":"10.1016\/j.neunet.2024.107044_b34","doi-asserted-by":"crossref","unstructured":"Li, Ang, & Pearl, Judea (2024). Probabilities of causation with nonbinary treatment and effect. In Proceedings of the AAAI conference on artificial intelligence, Vol. 38 (pp. 20465\u201320472).","DOI":"10.1609\/aaai.v38i18.30030"},{"issue":"7","key":"10.1016\/j.neunet.2024.107044_b35","doi-asserted-by":"crossref","first-page":"7328","DOI":"10.1109\/TKDE.2022.3193725","article-title":"OOD-GNN: out-of-distribution generalized graph neural network","volume":"35","author":"Li","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2024.107044_b36","first-page":"30277","article-title":"Graphde: A generative framework for debiased learning and out-of-distribution detection on graphs","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b37","series-title":"Identifying semantic component for robust molecular property prediction","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2024.107044_b38","first-page":"11828","article-title":"Learning invariant graph representations for out-of-distribution generalization","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b39","doi-asserted-by":"crossref","unstructured":"Liu, Yang, Ao, Xiang, Feng, Fuli, Ma, Yunshan, Li, Kuan, Chua, Tat-Seng, et al. (2023). FLOOD: A Flexible Invariant Learning Framework for Out-of-Distribution Generalization on Graphs. In Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (pp. 1548\u20131558).","DOI":"10.1145\/3580305.3599355"},{"issue":"3","key":"10.1016\/j.neunet.2024.107044_b40","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TPAMI.2015.2456899","article-title":"Classification with noisy labels by importance reweighting","volume":"38","author":"Liu","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2024.107044_b41","doi-asserted-by":"crossref","unstructured":"Liu, Gang, Zhao, Tong, Xu, Jiaxin, Luo, Tengfei, & Jiang, Meng (2022a). Graph rationalization with environment-based augmentations. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (pp. 1069\u20131078).","DOI":"10.1145\/3534678.3539347"},{"key":"10.1016\/j.neunet.2024.107044_b42","series-title":"Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"1069","article-title":"Graph rationalization with environment-based augmentations","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2024.107044_b43","series-title":"International conference on machine learning","first-page":"15524","article-title":"Interpretable and generalizable graph learning via stochastic attention mechanism","author":"Miao","year":"2022"},{"key":"10.1016\/j.neunet.2024.107044_b44","series-title":"Proceedings of the thirty-first international joint conference on artificial intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022","first-page":"2712","article-title":"Causes of effects: Learning individual responses from population data","author":"Mueller","year":"2022"},{"key":"10.1016\/j.neunet.2024.107044_b45","first-page":"21247","article-title":"A measure-theoretic approach to kernel conditional mean embeddings","volume":"33","author":"Park","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b46","series-title":"Causality","author":"Pearl","year":"2009"},{"key":"10.1016\/j.neunet.2024.107044_b47","doi-asserted-by":"crossref","unstructured":"Pearl, Judea (2022). Probabilities of causation: three counterfactual interpretations and their identification. In Probabilistic and causal inference: the works of judea pearl (pp. 317\u2013372).","DOI":"10.1145\/3501714.3501735"},{"issue":"2","key":"10.1016\/j.neunet.2024.107044_b48","first-page":"3","article-title":"Models, reasoning and inference","volume":"19","author":"Pearl","year":"2000","journal-title":"Cambridge, UK: CambridgeUniversityPress"},{"issue":"8","key":"10.1016\/j.neunet.2024.107044_b49","first-page":"8846","article-title":"Graph neural networks for intelligent transportation systems: A survey","volume":"24","author":"Rahmani","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2024.107044_b50","series-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"Sagawa","year":"2019"},{"key":"10.1016\/j.neunet.2024.107044_b51","series-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"10.1016\/j.neunet.2024.107044_b52","first-page":"26475","article-title":"Identification and estimation of joint probabilities of potential outcomes in observational studies with covariate information","volume":"34","author":"Shingaki","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b53","doi-asserted-by":"crossref","unstructured":"Song, Ying, Zheng, Shuangjia, Niu, Zhangming, Fu, Zhang-Hua, Lu, Yutong, & Yang, Yuedong (2021). Communicative Representation Learning on Attributed Molecular Graphs. In Proceedings of the twenty-ninth international joint conference on artificial intelligence. ISBN: 9780999241165.","DOI":"10.24963\/ijcai.2020\/392"},{"key":"10.1016\/j.neunet.2024.107044_b54","doi-asserted-by":"crossref","unstructured":"Sui, Yongduo, Wang, Xiang, Wu, Jiancan, Lin, Min, He, Xiangnan, & Chua, Tat-Seng (2022). Causal attention for interpretable and generalizable graph classification. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining (pp. 1696\u20131705).","DOI":"10.1145\/3534678.3539366"},{"key":"10.1016\/j.neunet.2024.107044_b55","first-page":"12096","article-title":"Does GNN pretraining help molecular representation?","volume":"35","author":"Sun","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b56","series-title":"Computer vision\u2013ECCV 2016 workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, proceedings, part III 14","first-page":"443","article-title":"Deep coral: Correlation alignment for deep domain adaptation","author":"Sun","year":"2016"},{"key":"10.1016\/j.neunet.2024.107044_b57","doi-asserted-by":"crossref","unstructured":"Tan, Juntao, Geng, Shijie, Fu, Zuohui, Ge, Yingqiang, Xu, Shuyuan, Li, Yunqi, et al. (2022). Learning and evaluating graph neural network explanations based on counterfactual and factual reasoning. In Proceedings of the ACM web conference 2022 (pp. 1018\u20131027).","DOI":"10.1145\/3485447.3511948"},{"issue":"1\u20134","key":"10.1016\/j.neunet.2024.107044_b58","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1018912507879","article-title":"Probabilities of causation: Bounds and identification","volume":"28","author":"Tian","year":"2000","journal-title":"Annals of Mathematics and Artificial Intelligence"},{"key":"10.1016\/j.neunet.2024.107044_b59","first-page":"28131","article-title":"An empirical investigation of domain generalization with empirical risk minimizers","volume":"34","author":"Vedantam","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b60","series-title":"Graph attention networks","author":"Velickovic","year":"2017"},{"key":"10.1016\/j.neunet.2024.107044_b61","first-page":"16451","article-title":"Self-supervised learning with data augmentations provably isolates content from style","volume":"34","author":"Von K\u00fcgelgen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b62","series-title":"Uncertainty in artificial intelligence","first-page":"1382","article-title":"Local explanations via necessity and sufficiency: Unifying theory and practice","author":"Watson","year":"2021"},{"key":"10.1016\/j.neunet.2024.107044_b63","series-title":"International conference on machine learning","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2024.107044_b64","series-title":"The tenth international conference on learning representations, ICLR 2022, virtual event, April 25-29, 2022","article-title":"Discovering invariant rationales for graph neural networks","author":"Wu","year":"2022"},{"key":"10.1016\/j.neunet.2024.107044_b65","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3360623","article-title":"A time-consistency curriculum for learning from instance-dependent noisy labels","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"16","key":"10.1016\/j.neunet.2024.107044_b66","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2019","journal-title":"Journal of Medicinal Chemistry"},{"key":"10.1016\/j.neunet.2024.107044_b67","series-title":"7th international conference on learning representations, ICLR 2019, New Orleans, La, USA, May 6-9, 2019","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2019"},{"key":"10.1016\/j.neunet.2024.107044_b68","series-title":"International conference on machine learning","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","author":"Xu","year":"2018"},{"key":"10.1016\/j.neunet.2024.107044_b69","first-page":"12964","article-title":"Learning substructure invariance for out-of-distribution molecular representations","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b70","unstructured":"Yang, Mengyue, Zhang, Yonggang, Fang, Zhen, Du, Yali, Liu, Furui, Ton, Jean-Francois, et al. (2023). Invariant Learning via Probability of Sufficient and Necessary Causes. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine (Eds.), Advances in neural information processing systems 36: annual conference on neural information processing systems 2023, NeurIPS 2023, New Orleans, La, USA, December 10 - 16, 2023."},{"key":"10.1016\/j.neunet.2024.107044_b71","article-title":"Gnnexplainer: Generating explanations for graph neural networks","volume":"32","author":"Ying","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b72","article-title":"Hierarchical graph representation learning with differentiable pooling","volume":"31","author":"Ying","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b73","series-title":"6th international conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, conference track proceedings","article-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2024.107044_b74","doi-asserted-by":"crossref","unstructured":"Zhang, Xingxuan, Cui, Peng, Xu, Renzhe, Zhou, Linjun, He, Yue, & Shen, Zheyan (2021). Deep stable learning for out-of-distribution generalization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5372\u20135382).","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"10.1016\/j.neunet.2024.107044_b75","series-title":"International conference on machine learning","first-page":"26548","article-title":"Partial counterfactual identification from observational and experimental data","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2024.107044_b76","first-page":"34940","article-title":"Multi-instance causal representation learning for instance label prediction and out-of-distribution generalization","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2024.107044_b77","first-page":"12827","article-title":"Uncertainty aware semi-supervised learning on graph data","volume":"33","author":"Zhao","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024009730?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608024009730?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T05:25:54Z","timestamp":1744262754000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608024009730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":77,"alternative-id":["S0893608024009730"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2024.107044","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Unifying invariant and variant features for graph out-of-distribution via probability of necessity and sufficiency","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2024.107044","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107044"}}