{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:44:44Z","timestamp":1778154284111,"version":"3.51.4"},"reference-count":57,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2023,1,30]]},"abstract":"<jats:p>Dynamic link prediction is an important component of the dynamic network analysis with many real-world applications. Currently, most advancements focus on analyzing link-defined neighborhoods with graph convolutional networks (GCN), while ignoring the influence of higher-order structural and temporal interacting features on link formation. Therefore, based on recent progress in modeling temporal graphs, we propose a novel temporal motif-based attentional graph convolutional network model (TMAGCN) for dynamic link prediction. As dynamic graphs usually contain periodical patterns, we first propose a temporal motif matrix construction method to capture higher-order structural and temporal features, then introduce a spatial convolution operation following a temporal motif-attention mechanism to encode these features into node embeddings. Furthermore, we design two methods to combine multiple temporal motif-based attentions, a dynamic attention-based method and a reinforcement learning-based method, to allow each individual node to make the most of the relevant motif-based neighborhood to propagate and aggregate information in the graph convolutional layers. Experimental results on various real-world datasets demonstrate that the proposed model is superior to state-of-the-art baselines on the dynamic link prediction task. It also reveals that temporal motif can manifest the essential dynamic mechanism of the network.<\/jats:p>","DOI":"10.3233\/ida-216169","type":"journal-article","created":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T11:15:53Z","timestamp":1675163753000},"page":"241-268","source":"Crossref","is-referenced-by-count":4,"title":["Temporal motif-based attentional graph convolutional network for dynamic link prediction"],"prefix":"10.1177","volume":"27","author":[{"given":"Zheng","family":"Wu","sequence":"first","affiliation":[{"name":"Information Engineering University, Zhengzhou, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongchang","family":"Chen","sequence":"additional","affiliation":[{"name":"Information Engineering University, Zhengzhou, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Information Engineering University, Zhengzhou, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulong","family":"Pei","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zishuo","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai Maritime University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-216169_ref1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2020.09.039","article-title":"Link prediction based on feature representation and fusion","volume":"548","author":"Xiao","year":"2021","journal-title":"Information Sciences"},{"key":"10.3233\/IDA-216169_ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2020.11.043","article-title":"Exchange, adopt, evolve: Modeling the spreading of opinions through cognition and interaction in a social network","volume":"551","author":"Tang","year":"2021","journal-title":"Information Sciences"},{"key":"10.3233\/IDA-216169_ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"issue":"14","key":"10.3233\/IDA-216169_ref4","doi-asserted-by":"publisher","first-page":"i190","DOI":"10.1093\/bioinformatics\/btx252","article-title":"Predicting multicellular function through multi-layer tissue networks","volume":"33","author":"Zitnik","year":"2017","journal-title":"Bioinform"},{"key":"10.3233\/IDA-216169_ref5","doi-asserted-by":"publisher","first-page":"124289","DOI":"10.1016\/j.physa.2020.124289","article-title":"Link prediction techniques, applications, and performance: A survey","volume":"553","author":"Kumar","year":"2020","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"3","key":"10.3233\/IDA-216169_ref6","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.physrep.2012.03.001","article-title":"Temporal networks","volume":"519","author":"Holme","year":"2012","journal-title":"Physics Reports"},{"key":"10.3233\/IDA-216169_ref7","unstructured":"J.R. Foulds, C. DuBois, A.U. Asuncion, C.T. Butts and P. Smyth, A Dynamic Relational Infinite Feature Model for Longitudinal Social Networks, in: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2011, Fort Lauderdale, USA, April 11\u201313, 2011, JMLR Proceedings, Vol. 15, JMLR.org, 2011, pp.\u00a0287\u2013295."},{"key":"10.3233\/IDA-216169_ref8","unstructured":"M. Kim and J. Leskovec, Nonparametric Multi-group Membership Model for Dynamic Networks, in: Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5\u20138, 2013, Lake Tahoe, Nevada, United States, 2013, pp.\u00a01385\u20131393."},{"issue":"1","key":"10.3233\/IDA-216169_ref9","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s10618-015-0407-0","article-title":"Link prediction using time series of neighborhood-based node similarity scores","volume":"30","author":"G\u00fcnes","year":"2016","journal-title":"Data Min. Knowl. Discov."},{"key":"10.3233\/IDA-216169_ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2016.0068"},{"issue":"1","key":"10.3233\/IDA-216169_ref11","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.gpb.2016.01.004","article-title":"A bipartite network-based method for prediction of long non-coding RNA-protein interactions","volume":"14","author":"Ge","year":"2016","journal-title":"Genomics, Proteomics & Bioinformatics"},{"key":"10.3233\/IDA-216169_ref12","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.63"},{"issue":"1","key":"10.3233\/IDA-216169_ref13","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1145\/1217299.1217301","article-title":"Graph evolution: Densification and shrinking diameters","volume":"1","author":"Leskovec","year":"2007","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.3233\/IDA-216169_ref14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.33"},{"key":"10.3233\/IDA-216169_ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191526"},{"key":"10.3233\/IDA-216169_ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132918"},{"key":"10.3233\/IDA-216169_ref17","unstructured":"L. Zhou, Y. Yang, X. Ren, F. Wu and Y. Zhuang, Dynamic Network Embedding by Modeling Triadic Closure Process, in: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137, 2018, AAAI Press, 2018, pp. 571\u2013578."},{"key":"10.3233\/IDA-216169_ref18","unstructured":"Y. Pei, X. Du, G. Fletcher and M. Pechenizkiy, Dynamic network representation learning via gaussian embedding, in: NeurIPS 2019 Workshop on Graph Representation Learning, 2019."},{"key":"10.3233\/IDA-216169_ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159727"},{"key":"10.3233\/IDA-216169_ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018689"},{"key":"10.3233\/IDA-216169_ref24","doi-asserted-by":"crossref","unstructured":"Y. Zhu, H. Li, Y. Liao, B. Wang, Z. Guan, H. Liu and D. Cai, What to Do Next: Modeling User Behaviors by Time-LSTM, in: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19\u201325, 2017, ijcai.org, 2017, pp. 3602\u20133608.","DOI":"10.24963\/ijcai.2017\/504"},{"key":"10.3233\/IDA-216169_ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737631"},{"key":"10.3233\/IDA-216169_ref27","unstructured":"T.N. Kipf and M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings, OpenReview.net, 2017."},{"key":"10.3233\/IDA-216169_ref28","unstructured":"R. Trivedi, M. Farajtabar, P. Biswal and H. Zha, DyRep: Learning Representations over Dynamic Graphs, in: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019, OpenReview.net, 2019."},{"key":"10.3233\/IDA-216169_ref30","doi-asserted-by":"publisher","DOI":"10.1515\/9781400841356.217"},{"key":"10.3233\/IDA-216169_ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018731"},{"key":"10.3233\/IDA-216169_ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186900"},{"issue":"1","key":"10.3233\/IDA-216169_ref33","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/TNNLS.2018.2826529","article-title":"Estimation of Graphlet Counts in Massive Networks","volume":"30","author":"Rossi","year":"2019","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.3233\/IDA-216169_ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8462-3_6"},{"issue":"4","key":"10.3233\/IDA-216169_ref35","doi-asserted-by":"publisher","first-page":"69:1","DOI":"10.1145\/3012704","article-title":"A Survey of Link Prediction in Complex Networks","volume":"49","author":"Mart\u00ednez","year":"2017","journal-title":"ACM Comput. Surv."},{"issue":"4","key":"10.3233\/IDA-216169_ref36","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1007\/s10489-014-0631-0","article-title":"Link prediction in dynamic social networks by integrating different types of information","volume":"42","author":"Ibrahim","year":"2015","journal-title":"Appl. Intell."},{"key":"10.3233\/IDA-216169_ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/467"},{"key":"10.3233\/IDA-216169_ref38","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.ins.2015.10.036","article-title":"An efficient algorithm for link prediction in temporal uncertain social networks","volume":"331","author":"Ibrahim","year":"2016","journal-title":"Inf. Sci."},{"key":"10.3233\/IDA-216169_ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191526"},{"key":"10.3233\/IDA-216169_ref41","unstructured":"A. M.V. and M. L.S., Dynamic Link Prediction in Biomedical Domain, in: ICCVBIC 2019. Advances in Intelligent Systems and Computing, Springer Press, 2019, p.\u00a0vol 1108."},{"issue":"6","key":"10.3233\/IDA-216169_ref43","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1093\/bioinformatics\/btq091","article-title":"Biological network comparison using graphlet degree distribution","volume":"26","author":"Przulj","year":"2010","journal-title":"Bioinform."},{"key":"10.3233\/IDA-216169_ref44","doi-asserted-by":"publisher","first-page":"e369","DOI":"10.1371\/journal.pbio.0020369","article-title":"Motifs in brain networks","volume":"2","author":"Sporns","year":"2004","journal-title":"PLoS Biology"},{"key":"10.3233\/IDA-216169_ref45","doi-asserted-by":"publisher","first-page":"e106132","DOI":"10.1371\/journal.pone.0106132","article-title":"Identification of important nodes in directed biological networks: A network motif approach","volume":"9","author":"Wang","year":"2014","journal-title":"PloS One"},{"key":"10.3233\/IDA-216169_ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3041021.3055139"},{"key":"10.3233\/IDA-216169_ref47","doi-asserted-by":"crossref","unstructured":"J. Ugander, L. Backstrom and J. Kleinberg, Subgraph Frequencies: Mapping the Empirical and Extremal Geography of Large Graph Collections, in: WWW 2013 \u2013 Proceedings of the 22nd International Conference on World Wide Web, 2013.","DOI":"10.1145\/2488388.2488502"},{"key":"10.3233\/IDA-216169_ref48","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1126\/science.aad9029","article-title":"Higher-order organization of complex networks","volume":"353","author":"Benson","year":"2016","journal-title":"Science"},{"key":"10.3233\/IDA-216169_ref49","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2018.8439897"},{"key":"10.3233\/IDA-216169_ref50","unstructured":"H. Zhao, X. Xu, Y. Song, D.L. Lee, Z. Chen and H. Gao, Ranking Users in Social Networks With Higher-Order Structures, in: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137, 2018, AAAI Press, 2018, pp.\u00a0232\u2013240."},{"key":"10.3233\/IDA-216169_ref51","unstructured":"J. Zhang, J. Tang, Y. Zhong, Y. Mo, J. Li, G. Song, W. Hall and J. Sun, StructInf: Mining Structural Influence from Social Streams, in: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4\u20139, 2017, San Francisco, California, USA, AAAI Press, 2017, pp.\u00a073\u201380."},{"key":"10.3233\/IDA-216169_ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098069"},{"key":"10.3233\/IDA-216169_ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM.2018.8508729"},{"key":"10.3233\/IDA-216169_ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052597"},{"issue":"4","key":"10.3233\/IDA-216169_ref55","doi-asserted-by":"publisher","first-page":"43:1","DOI":"10.1145\/3059194","article-title":"TRI\u00c8ST: Counting local and global triangles in fully dynamic streams with fixed memory size","volume":"11","author":"Stefani","year":"2017","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.3233\/IDA-216169_ref56","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Li\u00f2 and Y. Bengi, Graph Attention Networks, in: International Conference on Learning Representations, 2018."},{"key":"10.3233\/IDA-216169_ref57","unstructured":"V. Mnih, N. Heess, A. Graves and koray kavukcuoglu, Recurrent Models of Visual Attention, in: Advances in Neural Information Processing Systems 27, Vol.\u00a027, 2014, pp.\u00a02204\u20132212."},{"issue":"4","key":"10.3233\/IDA-216169_ref58","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/MPRV.2011.79","article-title":"Sensing the \u201chealth state\u201d of a community","volume":"11","author":"Madan","year":"2012","journal-title":"IEEE Pervasive Computing"},{"key":"10.3233\/IDA-216169_ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"10.3233\/IDA-216169_ref60","unstructured":"X. Glorot and Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010, Chia Laguna Resort, Sardinia, Italy, May 13\u201315, 2010, JMLR Proceedings, Vol.\u00a09, JMLR.org, 2010, pp.\u00a0249\u2013256."},{"key":"10.3233\/IDA-216169_ref61","unstructured":"D.P. Kingma and J. Ba, Adam: A Method for Stochastic Optimization, in: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings, 2015."},{"issue":"86","key":"10.3233\/IDA-216169_ref62","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van\u00a0der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/IDA-216169_ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2953264"},{"issue":"3","key":"10.3233\/IDA-216169_ref64","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Machine Learning"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-216169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:19:46Z","timestamp":1777454386000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-216169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,30]]},"references-count":57,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ida-216169","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,30]]}}}