{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T07:04:58Z","timestamp":1779692698654,"version":"3.53.1"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2025QC624"],"award-info":[{"award-number":["ZR2025QC624"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2024MF034"],"award-info":[{"award-number":["ZR2024MF034"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["24YJAZH058"],"award-info":[{"award-number":["24YJAZH058"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["24YJCZH461"],"award-info":[{"award-number":["24YJCZH461"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502288"],"award-info":[{"award-number":["62502288"]}],"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":["62472263"],"award-info":[{"award-number":["62472263"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,8]]},"DOI":"10.1016\/j.neunet.2026.108854","type":"journal-article","created":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T06:39:17Z","timestamp":1773556757000},"page":"108854","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Handling distribution shifts on dynamic graphs via causal invariance principles"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3131-2723","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1131-2356","authenticated-orcid":false,"given":"Yafei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1774-5786","authenticated-orcid":false,"given":"Runshuo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6793-5216","authenticated-orcid":false,"given":"Qianyu","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5880-0225","authenticated-orcid":false,"given":"Zhongying","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6421-8223","authenticated-orcid":false,"given":"Qingtian","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"14","key":"10.1016\/j.neunet.2026.108854_bib0001","doi-asserted-by":"crossref","first-page":"4758","DOI":"10.3390\/s21144758","article-title":"Graph-based deep learning for medical diagnosis and analysis: Past, present and future","volume":"21","author":"Ahmedt-Aristizabal","year":"2021","journal-title":"Sensors"},{"issue":"5","key":"10.1016\/j.neunet.2026.108854_bib0002","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1038\/s41562-020-01024-1","article-title":"Evolutionary dynamics of higher-order interactions in social networks","volume":"5","author":"Alvarez-Rodriguez","year":"2021","journal-title":"Nature Human Behaviour"},{"key":"10.1016\/j.neunet.2026.108854_bib0003","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., & Lopez-Paz, D. (2019). Invariant risk minimization. arXiv: 1907.02893."},{"key":"10.1016\/j.neunet.2026.108854_bib0004","unstructured":"Bruna, J., Zaremba, W., Szlam, A., & LeCun, Y. (2013). Spectral networks and locally connected networks on graphs. arXiv: 1312.6203."},{"key":"10.1016\/j.neunet.2026.108854_bib0005","series-title":"2021 58Th ACM\/IEEE design automation conference (DAC)","first-page":"1201","article-title":"Dygnn: Algorithm and architecture support of dynamic pruning for graph neural networks","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2026.108854_bib0006","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"},{"key":"10.1016\/j.neunet.2026.108854_bib0007","unstructured":"Chen, Y., Zhang, Y., Yang, H., Ma, K., Xie, B., Liu, T., Han, B., & Cheng, J. (2022b). Invariance principle meets out-of-distribution generalization on graphs. arXiv: 2202.05441, 2(3), 5."},{"key":"10.1016\/j.neunet.2026.108854_bib0008","series-title":"11Th international conference on learning representations, ICLR 2023","article-title":"Do we really need complicated model architectures for temporal networks?","author":"Cong","year":"2023"},{"key":"10.1016\/j.neunet.2026.108854_bib0009","unstructured":"Goyal, P., Kamra, N., He, X., & Liu, Y. (2018). Dyngem: Deep embedding method for dynamic graphs. arXiv: 1805.11273."},{"key":"10.1016\/j.neunet.2026.108854_bib0010","doi-asserted-by":"crossref","DOI":"10.1109\/TNNLS.2024.3379735","article-title":"Deep learning for dynamic graphs: Models and benchmarks","author":"Gravina","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108854_bib0011","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/j.neuroimage.2017.12.052","article-title":"Metric learning with spectral graph convolutions on brain connectivity networks","volume":"169","author":"Ktena","year":"2018","journal-title":"NeuroImage"},{"key":"10.1016\/j.neunet.2026.108854_bib0012","series-title":"Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"1269","article-title":"Predicting dynamic embedding trajectory in temporal interaction networks","author":"Kumar","year":"2019"},{"key":"10.1016\/j.neunet.2026.108854_bib0013","unstructured":"Li, G., Koutra, D., & Yan, Y. (2023). Size generalization of graph neural networks on biological data: Insights and practices from the spectral perspective. arXiv: 2305.15611."},{"key":"10.1016\/j.neunet.2026.108854_bib0014","unstructured":"Longa, A., Lachi, V., Santin, G., Bianchini, M., Lepri, B., Lio, P., Scarselli, F., & Passerini, A. (2023). Graph neural networks for temporal graphs: State of the art, open challenges, and opportunities. arXiv: 2302.01018."},{"key":"10.1016\/j.neunet.2026.108854_bib0015","series-title":"2022\u202fIEEE 25Th international conference on intelligent transportation systems (ITSC)","first-page":"687","article-title":"A multidimensional graph fourier transformation neural network for vehicle trajectory prediction","author":"Neumeier","year":"2022"},{"key":"10.1016\/j.neunet.2026.108854_bib0016","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5363","article-title":"Evolvegcn: Evolving graph convolutional networks for dynamic graphs","volume":"vol. 34","author":"Pareja","year":"2020"},{"key":"10.1016\/j.neunet.2026.108854_bib0017","series-title":"International conference on learning representations","article-title":"Learning mesh-based simulation with graph networks","author":"Pfaff","year":"2020"},{"key":"10.1016\/j.neunet.2026.108854_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"27631","article-title":"Improving out-of-distribution generalization in graphs via hierarchical semantic environments","author":"Piao","year":"2024"},{"key":"10.1016\/j.neunet.2026.108854_bib0019","first-page":"32928","article-title":"Towards better evaluation for dynamic link prediction","volume":"35","author":"Poursafaei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108854_bib0020","series-title":"Icml 2020 workshop on graph representation learning","article-title":"Temporal graph networks for deep learning on dynamic graphs","author":"Rossi","year":"2020"},{"key":"10.1016\/j.neunet.2026.108854_bib0021","series-title":"Proceedings of the 13th international conference on web search and data mining","first-page":"519","article-title":"Dysat: Deep neural representation learning on dynamic graphs via self-attention networks","author":"Sankar","year":"2020"},{"key":"10.1016\/j.neunet.2026.108854_bib0022","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1109\/TPAMI.2025.3631584","article-title":"Evolving graph learning for out-of-distribution generalization in non-stationary environments","volume":"48","author":"Sun","year":"2025","journal-title":"IEEE Transactions on pattern analysis and machine intelligence"},{"key":"10.1016\/j.neunet.2026.108854_bib0023","series-title":"The twelfth international conference on learning representations","article-title":"Freedyg: Frequency enhanced continuous-time dynamic graph model for link prediction","author":"Tian","year":"2024"},{"key":"10.1016\/j.neunet.2026.108854_bib0024","series-title":"International conference on learning representations","article-title":"Dyrep: Learning representations over dynamic graphs","author":"Trivedi","year":"2019"},{"key":"10.1016\/j.neunet.2026.108854_bib0025","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"1615","article-title":"Environment agnostic invariant risk minimization for classification of sequential datasets","author":"Venkateswaran","year":"2021"},{"key":"10.1016\/j.neunet.2026.108854_bib0026","series-title":"Proceedings of the ACM web conference 2022","first-page":"3562","article-title":"Causal representation learning for out-of-distribution recommendation","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108854_bib0027","series-title":"International conference on learning representations (ICLR)","article-title":"Inductive representation learning in temporal networks via causal anonymous walks","author":"Wang","year":"2021"},{"key":"10.1016\/j.neunet.2026.108854_bib0028","unstructured":"Wu, Q., Zhang, H., Yan, J., & Wipf, D. (2022a). Handling distribution shifts on graphs: An invariance perspective. arXiv: 2202.02466."},{"key":"10.1016\/j.neunet.2026.108854_bib0029","unstructured":"Wu, Y.-X., Wang, X., Zhang, A., He, X., & Chua, T.-S. (2022b). Discovering invariant rationales for graph neural networks. arXiv: 2201.12872."},{"key":"10.1016\/j.neunet.2026.108854_bib0030","series-title":"8Th international conference on learning representations, ICLR, 26-30","article-title":"Inductive representation learning on temporal graphs","author":"Xu","year":"2020"},{"key":"10.1016\/j.neunet.2026.108854_bib0031","doi-asserted-by":"crossref","first-page":"43460","DOI":"10.1109\/ACCESS.2024.3378111","article-title":"Dynamic graph representation learning with neural networks: A survey","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.108854_bib0032","series-title":"International conference on machine learning","first-page":"11975","article-title":"From local structures to size generalization in graph neural networks","author":"Yehudai","year":"2021"},{"issue":"4","key":"10.1016\/j.neunet.2026.108854_bib0033","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1109\/TKDE.2023.3309982","article-title":"Continuous-time user preference modelling for temporal sets prediction","volume":"36","author":"Yu","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2026.108854_bib0034","first-page":"67686","article-title":"Towards better dynamic graph learning: New architecture and unified library","volume":"36","author":"Yu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108854_bib0035","series-title":"Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"3309","article-title":"Dyted: Disentangled representation learning for discrete-time dynamic graph","author":"Zhang","year":"2023"},{"issue":"5","key":"10.1016\/j.neunet.2026.108854_bib0036","first-page":"4741","article-title":"Dynamic graph neural networks for sequential recommendation","volume":"35","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2026.108854_bib0037","series-title":"10Th international conference on learning representations (ICLR 2022)","article-title":"Adversarial robustness through the lens of causality","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108854_bib0038","first-page":"6074","article-title":"Dynamic graph neural networks under spatio-temporal distribution shift","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108854_bib0039","first-page":"6619","article-title":"Spectral invariant learning for dynamic graphs under distribution shifts","volume":"36","author":"Zhang","year":"2023","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:S0893608026003151?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003151?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T06:37:27Z","timestamp":1779691047000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003151"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":39,"alternative-id":["S0893608026003151"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108854","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Handling distribution shifts on dynamic graphs via causal invariance principles","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108854","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108854"}}