{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:24:31Z","timestamp":1783635871574,"version":"3.55.0"},"reference-count":50,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72572095"],"award-info":[{"award-number":["72572095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2023MF070"],"award-info":[{"award-number":["ZR2023MF070"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.knosys.2026.116305","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T06:57:46Z","timestamp":1779865066000},"page":"116305","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CIRRUS: A contextual interaction routing residual and unified spectral architecture for temporal graph representation learning"],"prefix":"10.1016","volume":"348","author":[{"given":"Xianghui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8870-572X","authenticated-orcid":false,"given":"Liqing","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116305_b1","series-title":"Companion Proceedings of the the Web Conference 2018","first-page":"969","article-title":"Continuous-time dynamic network embeddings","author":"Nguyen","year":"2018"},{"issue":"1","key":"10.1016\/j.knosys.2026.116305_b2","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/TKDE.2025.3621291","article-title":"A comprehensive survey of dynamic graph neural networks: models, frameworks, benchmarks, experiments and challenges","volume":"38","author":"Feng","year":"2026","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116305_b3","series-title":"Temporal graph networks for deep learning on dynamic graphs","author":"Rossi","year":"2020"},{"key":"10.1016\/j.knosys.2026.116305_b4","series-title":"Advances in Neural Information Processing Systems","article-title":"DyG-Mamba: Continuous state space modeling on dynamic graphs","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2026.116305_b5","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.knosys.2026.116305_b6","first-page":"5363","article-title":"EvolveGCN: Evolving graph convolutional networks for dynamic graphs","volume":"vol. 34","author":"Pareja","year":"2020"},{"key":"10.1016\/j.knosys.2026.116305_b7","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.knosys.2026.116305_b8","series-title":"International Conference on Learning Representations","article-title":"DyRep: Learning representations over dynamic graphs","author":"Trivedi","year":"2019"},{"key":"10.1016\/j.knosys.2026.116305_b9","series-title":"International Conference on Learning Representations","article-title":"Inductive representation learning on temporal graphs","author":"Xu","year":"2020"},{"key":"10.1016\/j.knosys.2026.116305_b10","first-page":"67686","article-title":"Towards better dynamic graph learning: New architecture and unified library","volume":"vol. 36","author":"Yu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116305_b11","series-title":"Do we really need complicated model architectures for temporal networks?","author":"Cong","year":"2023"},{"key":"10.1016\/j.knosys.2026.116305_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112245","article-title":"MTdyg: Multi-scale Transformers with continuous time dynamic graph model for link prediction","volume":"300","author":"Xu","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116305_b13","series-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","first-page":"2245","article-title":"TIDFormer: Exploiting temporal and interactive dynamics makes a great dynamic graph transformer","author":"Peng","year":"2025"},{"issue":"3","key":"10.1016\/j.knosys.2026.116305_b14","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.1109\/TKDE.2026.3656264","article-title":"Structure-aware model for representation learning on temporal graphs","volume":"38","author":"Sun","year":"2026","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116305_b15","series-title":"DynGEM: Deep embedding method for dynamic graphs","author":"Goyal","year":"2018"},{"key":"10.1016\/j.knosys.2026.116305_b16","series-title":"Proceedings of the 2021 International Conference on Management of Data","first-page":"2628","article-title":"APAN: Asynchronous propagation attention network for real time temporal graph embedding","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116305_b17","series-title":"International Conference on Learning Representations","article-title":"Inductive representation learning in temporal networks via causal anonymous walks","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116305_b18","series-title":"TCL: Transformer-based dynamic graph modelling via contrastive learning","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116305_b19","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"4722","article-title":"Repeat-aware neighbor sampling for dynamic graph learning","author":"Zou","year":"2024"},{"key":"10.1016\/j.knosys.2026.116305_b20","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","article-title":"Representation learning of temporal graphs with structural roles","author":"Du","year":"2024"},{"issue":"9","key":"10.1016\/j.knosys.2026.116305_b21","doi-asserted-by":"crossref","first-page":"2075","DOI":"10.14778\/3598581.3598583","article-title":"Temporal SIR-GN: Efficient and effective structural representation learning for temporal graphs","volume":"16","author":"Layne","year":"2023","journal-title":"Proc. VLDB Endow."},{"key":"10.1016\/j.knosys.2026.116305_b22","series-title":"Proceedings of the ACM Web Conference 2023","first-page":"478","article-title":"TIGER: Temporal interaction graph embedding with restarts","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116305_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109633","article-title":"Dual-branch spatio-temporal graph neural networks for pedestrian trajectory prediction","volume":"142","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116305_b24","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"vol. 29","author":"Defferrard","year":"2016"},{"key":"10.1016\/j.knosys.2026.116305_b25","series-title":"International Conference on Learning Representations","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.knosys.2026.116305_b26","series-title":"International Conference on Learning Representations","article-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2021"},{"key":"10.1016\/j.knosys.2026.116305_b27","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4296","article-title":"FNet: Mixing tokens with Fourier transforms","author":"Lee-Thorp","year":"2022"},{"key":"10.1016\/j.knosys.2026.116305_b28","first-page":"980","article-title":"Global filter networks for image classification","volume":"vol. 34","author":"Rao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116305_b29","first-page":"27268","article-title":"FEDformer: Frequency enhanced decomposed transformer for long term series forecasting","volume":"vol. 162","author":"Zhou","year":"2022"},{"key":"10.1016\/j.knosys.2026.116305_b30","first-page":"17766","article-title":"Spectral temporal graph neural network for multivariate time-series forecasting","volume":"vol. 33","author":"Cao","year":"2020"},{"key":"10.1016\/j.knosys.2026.116305_b31","first-page":"69638","article-title":"FourierGNN: Rethinking multivariate time series forecasting from a pure graph perspective","volume":"vol. 36","author":"Yi","year":"2023"},{"key":"10.1016\/j.knosys.2026.116305_b32","series-title":"International Conference on Learning Representations","article-title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","author":"Wu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116305_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112053","article-title":"TGFormer: Towards temporal graph transformer with auto-correlation mechanism","volume":"170","author":"Chen","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.knosys.2026.116305_b34","series-title":"Proceedings of the ACM Web Conference 2026","first-page":"487","article-title":"Exploring sequential dynamics on temporal graphs via composite filtering","author":"Xu","year":"2026"},{"key":"10.1016\/j.knosys.2026.116305_b35","series-title":"Proceedings of the ACM Web Conference 2025","first-page":"3918","article-title":"Ranking on dynamic graphs: An effective and robust band-pass disentangled approach","author":"Li","year":"2025"},{"key":"10.1016\/j.knosys.2026.116305_b36","series-title":"International Conference on Learning Representations","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.knosys.2026.116305_b37","series-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020"},{"key":"10.1016\/j.knosys.2026.116305_b38","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume":"vol. 119","author":"Hassani","year":"2020"},{"key":"10.1016\/j.knosys.2026.116305_b39","series-title":"Proceedings of the Web Conference 2021","first-page":"2069","article-title":"Graph contrastive learning with adaptive augmentation","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116305_b40","first-page":"24332","article-title":"ProGCL: Rethinking hard negative mining in graph contrastive learning","volume":"vol. 162","author":"Xia","year":"2022"},{"issue":"9","key":"10.1016\/j.knosys.2026.116305_b41","doi-asserted-by":"crossref","first-page":"11681","DOI":"10.1109\/TNNLS.2023.3339770","article-title":"Affinity uncertainty-based hard negative mining in graph contrastive learning","volume":"35","author":"Niu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"6","key":"10.1016\/j.knosys.2026.116305_b42","doi-asserted-by":"crossref","first-page":"10479","DOI":"10.1109\/TNNLS.2025.3545111","article-title":"Unifying attribute and structure preservation for enhanced graph contrastive learning","volume":"36","author":"Chen","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116305_b43","series-title":"International Conference on Learning Representations","article-title":"Large scale representation learning on graphs via bootstrapping","author":"Thakoor","year":"2022"},{"key":"10.1016\/j.knosys.2026.116305_b44","series-title":"2024 IEEE 40th International Conference on Data Engineering","first-page":"1199","article-title":"CPDG: A contrastive pre-training method for dynamic graph neural networks","author":"Bei","year":"2024"},{"key":"10.1016\/j.knosys.2026.116305_b45","series-title":"Machine Learning and Knowledge Discovery in Databases","first-page":"683","article-title":"Temporal graph representation learning with adaptive augmentation contrastive","author":"Chen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116305_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2024.120499","article-title":"A deep contrastive framework for unsupervised temporal link prediction in dynamic networks","volume":"667","author":"Jiao","year":"2024","journal-title":"Inform. Sci."},{"issue":"6","key":"10.1016\/j.knosys.2026.116305_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103847","article-title":"Edge contrastive learning for link prediction","volume":"61","author":"Liu","year":"2024","journal-title":"Inf. Process. Manage."},{"issue":"4","key":"10.1016\/j.knosys.2026.116305_b48","doi-asserted-by":"crossref","first-page":"4216","DOI":"10.1109\/TKDE.2021.3131584","article-title":"Self-supervised learning on graphs: Contrastive, generative, or predictive","volume":"35","author":"Wu","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116305_b49","first-page":"32928","article-title":"Towards better evaluation for dynamic link prediction","volume":"vol. 35","author":"Poursafaei","year":"2022"},{"key":"10.1016\/j.knosys.2026.116305_b50","first-page":"141153","article-title":"Improving temporal link prediction via temporal walk matrix projection","volume":"vol. 37","author":"Lu","year":"2024"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126010312?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126010312?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T22:11:32Z","timestamp":1783635092000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126010312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":50,"alternative-id":["S0950705126010312"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116305","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CIRRUS: A contextual interaction routing residual and unified spectral architecture for temporal graph representation learning","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116305","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116305"}}