{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:05Z","timestamp":1740182405938,"version":"3.37.3"},"reference-count":39,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61861037"],"award-info":[{"award-number":["61861037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62002297"],"award-info":[{"award-number":["62002297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100018571","name":"Guangxi Science and Technology Base and Talent Special Project","doi-asserted-by":"crossref","award":["2021AC19394"],"award-info":[{"award-number":["2021AC19394"]}],"id":[{"id":"10.13039\/501100018571","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Representation learning over graph networks has recently gained popularity, with many models showing promising results. However, several challenges remain: (1) most methods are designed for static or discrete-time dynamic graphs; (2) existing continuous-time dynamic graph algorithms focus on a single evolving perspective; and (3) many continuous-time dynamic graph approaches necessitate numerous temporal neighbors to capture long-term dependencies. In response, this paper introduces a Multi-Perspective Feedback-Attention Coupling (MPFA) model. MPFA incorporates information from both evolving and original perspectives to effectively learn the complex dynamics of dynamic graph evolution processes. The evolving perspective considers the current state of historical interaction events of nodes and uses a temporal attention module to aggregate current state information. This perspective also makes it possible to capture long-term dependencies of nodes using a small number of temporal neighbors. Meanwhile, the original perspective utilizes a feedback attention module with growth characteristic coefficients to aggregate the original state information of node interactions. Experimental results on one dataset organized by ourselves and seven public datasets validate the effectiveness and competitiveness of our proposed model.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad66af","type":"journal-article","created":{"date-parts":[[2024,7,23]],"date-time":"2024-07-23T15:52:03Z","timestamp":1721749923000},"page":"035033","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-perspective feedback-attention coupling model for continuous-time dynamic graphs"],"prefix":"10.1088","volume":"5","author":[{"given":"Xiaobo","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8874-8886","authenticated-orcid":true,"given":"Yan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Che","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Liying","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhanheng","family":"Chen","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,8,5]]},"reference":[{"key":"mlstad66afbib1","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1145\/2939672.2939754","article-title":"node2vec: Scalable feature learning for networks","author":"Grover","year":"2016"},{"key":"mlstad66afbib2","doi-asserted-by":"publisher","first-page":"5171","DOI":"10.5555\/3327345.3327423","article-title":"Link prediction based on graph neural networks","author":"Zhang","year":"2018","journal-title":"Proc. of the 32nd Int. Conf. on Neural Information Processing Systems vol 31"},{"key":"mlstad66afbib3","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1109\/ICDMW.2017.20","article-title":"Distributed representations of subgraphs","author":"Adhikari","year":"2017"},{"key":"mlstad66afbib4","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1609\/aaai.v34i01.5470","article-title":"Spatio-temporal graph structure learning for traffic forecasting","volume":"vol 34","author":"Zhang","year":"2020"},{"key":"mlstad66afbib5","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1109\/TMM.2021.3138298","article-title":"Dualgnn: Dual graph neural network for multimedia recommendation","volume":"25","author":"Wang","year":"2021","journal-title":"IEEE Trans. on Multimedia"},{"article-title":"subgraph2vec Learning distributed representations of rooted sub-graphs from large graphs","year":"2016","author":"Narayanan","key":"mlstad66afbib6"},{"key":"mlstad66afbib7","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1145\/2783258.2783417","article-title":"Deep graph kernels","author":"Yanardag","year":"2015"},{"article-title":"Graph attention networks","year":"2017","author":"Veli\u010dkovi\u0107","key":"mlstad66afbib8"},{"key":"mlstad66afbib9","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.5555\/3294771.3294869","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems vol"},{"key":"mlstad66afbib10","first-page":"362","article-title":"Structured sequence modeling with graph convolutional recurrent networks","author":"Seo","year":"2018"},{"key":"mlstad66afbib11","first-page":"301","article-title":"Learning to represent the evolution of dynamic graphs with recurrent models","author":"Taheri","year":"2019"},{"author":"Chen","key":"mlstad66afbib12","article-title":"Evolving graph convolutional networks for dynamic graphs"},{"key":"mlstad66afbib13","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1016\/j.ifacol.2018.03.074","article-title":"Learning graph dynamics using deep neural networks","volume":"51","author":"Narayan","year":"2018","journal-title":"IFAC-PapersOnLine"},{"key":"mlstad66afbib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107000","article-title":"Dynamic graph convolutional networks","volume":"97","author":"Manessi","year":"2020","journal-title":"Pattern Recognit."},{"key":"mlstad66afbib15","first-page":"519","article-title":"Dysat: Deep neural representation learning on dynamic graphs via self-attention networks","author":"Sankar","year":"2020"},{"key":"mlstad66afbib16","first-page":"1279","article-title":"Predicting path failure in time-evolving graphs","author":"Li","year":"2019"},{"key":"mlstad66afbib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.06.024","article-title":"dyngraph2vec: Capturing network dynamics using dynamic graph representation learning","volume":"187","author":"Goyal","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"mlstad66afbib18","first-page":"536","article-title":"Dyngraphgan: dynamic graph embedding via generative adversarial networks","author":"Xiong","year":"2019"},{"key":"mlstad66afbib19","first-page":"719","article-title":"Streaming graph neural networks","author":"Ma","year":"2020"},{"key":"mlstad66afbib20","first-page":"2086","article-title":"Dynamic network embedding: An extended approach for skip-gram based network embedding","volume":"2018","author":"Du","year":"2018","journal-title":"IJCAI"},{"article-title":"Dyrep: Learning representations over dynamic graphs","year":"2019","author":"Trivedi","key":"mlstad66afbib21"},{"key":"mlstad66afbib22","first-page":"969","article-title":"Continuous-time dynamic network embeddings","author":"Nguyen","year":"2018"},{"key":"mlstad66afbib23","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.eswa.2016.03.033","article-title":"An adaptive random walk sampling method on dynamic community detection","volume":"58","author":"Xin","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"mlstad66afbib24","first-page":"1269","article-title":"Predicting dynamic embedding trajectory in temporal interaction networks","author":"Kumar","year":"2019"},{"article-title":"Temporal graph networks for deep learning on dynamic graphs","year":"2020","author":"Rossi","key":"mlstad66afbib25"},{"article-title":"Inductive representation learning on temporal graphs,\u201d","year":"2020","author":"Xu","key":"mlstad66afbib26"},{"article-title":"Tcl Transformer-based dynamic graph modelling via contrastive learning","year":"2021","author":"Wang","key":"mlstad66afbib27"},{"article-title":"Towards better dynamic graph learning: New architecture and unified library","year":"2023","author":"Yu","key":"mlstad66afbib28"},{"article-title":"Inductive representation learning in temporal networks via causal anonymous walks","year":"2021","author":"Wang","key":"mlstad66afbib29"},{"key":"mlstad66afbib30","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 vol"},{"key":"mlstad66afbib31","first-page":"115","article-title":"Learning precise timing with lstm recurrent networks","volume":"3","author":"Gers","year":"2002","journal-title":"J. Mach. Learn. Res."},{"article-title":"Spectral networks and locally connected networks on graphs","year":"2013","author":"Bruna","key":"mlstad66afbib32"},{"article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","author":"Kipf","key":"mlstad66afbib33"},{"key":"mlstad66afbib34","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstad66afbib35","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504947","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"Yan","year":"2018"},{"article-title":"Generative adversarial networks: A survey and taxonomy","year":"2019","author":"Wang","key":"mlstad66afbib36"},{"key":"mlstad66afbib37","doi-asserted-by":"publisher","first-page":"10701","DOI":"10.5555\/3454287.3455247","article-title":"Variational graph recurrent neural networks","volume":"32","author":"Hajiramezanali","year":"2019","journal-title":"Advances in Neural Information Processing Systems vol"},{"key":"mlstad66afbib38","first-page":"447","article-title":"evolve2vec: Learning network representations using temporal unfolding","author":"Bastas","year":"2019"},{"article-title":"Do we really need complicated model architectures for temporal networks?","year":"2023","author":"Cong","key":"mlstad66afbib39"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T11:09:57Z","timestamp":1722856197000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad66af"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,5]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad66af","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2024,8,5]]},"assertion":[{"value":"Multi-perspective feedback-attention coupling model for continuous-time dynamic graphs","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-04-23","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}