{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:47:48Z","timestamp":1762177668506,"version":"3.38.0"},"reference-count":38,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2024,2,3]]},"abstract":"<jats:p>Temporal link prediction based on graph neural networks has become a hot spot in the field of complex networks. To solve the problems of the existing temporal link prediction methods based on graph neural networks do not consider the future time-domain features and spatial-domain features are limited used, this paper proposes a novel temporal link prediction method based on two streams adaptive graph neural networks. Firstly, the network topology features are extracted from the micro, meso, and middle perspectives. Combined with the adaptive mechanism of convolution and self-attention, the preprocessing of the feature extraction is more effective; Secondly, an extended bi-directional long short-term memory network is proposed, which uses graph convolution to process topological features, and recursively learns the state vectors of the target snapshot by using the future time-domain information and the past historical information; Thirdly, the location coding is replaced by the time-coding for the transformer mechanism, so that past information and future information can be learned from each other, and the time-domain information of the network can be further mined; Finally, a novel two-stream network framework is proposed, which combines the processing results of point features and edge features. The experimental results on 9 data sets show that the proposed method has a better prediction effect and better robustness than the classical graph neural network methods.<\/jats:p>","DOI":"10.3233\/ida-237367","type":"journal-article","created":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T16:54:06Z","timestamp":1703868846000},"page":"77-97","source":"Crossref","is-referenced-by-count":1,"title":["TSAGNN: Temporal link predict method based on two stream adaptive graph neural network"],"prefix":"10.1177","volume":"28","author":[{"given":"Yuhang","family":"Zhu","sequence":"first","affiliation":[{"name":"Institute of Information Technology, PLA Strategic Support Force Information Engineering University, Zhengzhou, Henan, China"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[{"name":"Henan Xinda Wangyu Technology Co., Ltd, Henan Information Security Industry Demonstration Base, Zhengzhou, Henan, China"}]},{"given":"Haitao","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, PLA Strategic Support Force Information Engineering University, Zhengzhou, Henan, China"}]},{"given":"Shuxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, PLA Strategic Support Force Information Engineering University, Zhengzhou, Henan, China"}]},{"given":"Yingle","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Technology, PLA Strategic Support Force Information Engineering University, Zhengzhou, Henan, China"}]}],"member":"179","reference":[{"unstructured":"L.\u00a0Stankovic, D.\u00a0Mandic, M.\u00a0Dakovic, M.\u00a0Brajovic, B.\u00a0Scalzo and T.\u00a0Constantinides, Graph Signal Processing\u2013Part I: Graphs, Graph Spectra, and Spectral Clustering, arXiv preprint arXiv:1907.03467, (2019).","key":"10.3233\/IDA-237367_ref1"},{"issue":"2","key":"10.3233\/IDA-237367_ref2","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.1007\/s12652-020-02289-0","article-title":"Link prediction in dynamic networks using time-aware network embedding and time series forecasting","volume":"12","author":"Mohan","year":"2021","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"doi-asserted-by":"crossref","unstructured":"P.\u00a0Holme and J.\u00a0Saramaki, Temporal Network Theory 8 (2019), 375.","key":"10.3233\/IDA-237367_ref3","DOI":"10.1007\/978-3-030-23495-9"},{"issue":"1","key":"10.3233\/IDA-237367_ref4","doi-asserted-by":"crossref","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\u00fcne\u015f","year":"2016","journal-title":"Data Mining and Knowledge Discovery"},{"key":"10.3233\/IDA-237367_ref5","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1145\/2623330.2623732","article-title":"Deepwalk: Online learning of social representations","author":"Perozzi","year":"2014","journal-title":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining"},{"key":"10.3233\/IDA-237367_ref6","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1145\/2939672.2939754","article-title":"node2vec: Scalable feature learning for networks","author":"Grover","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining"},{"key":"10.3233\/IDA-237367_ref7","doi-asserted-by":"crossref","first-page":"1067","DOI":"10.1145\/2736277.2741093","article-title":"Line: Large-scale information network embedding","author":"Tang","year":"2015","journal-title":"Proceedings of the 24th international conference on world wide web"},{"key":"10.3233\/IDA-237367_ref8","doi-asserted-by":"crossref","first-page":"79143","DOI":"10.1109\/ACCESS.2021.3082932","article-title":"Foundations and modeling of dynamic networks using dynamic graph neural networks: A survey","volume":"9","author":"Skarding","year":"2021","journal-title":"IEEE Access"},{"issue":"3","key":"10.3233\/IDA-237367_ref9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/IJSSCI.2021070101","article-title":"Recurrent neural network (RNN) to analyse mental behaviour in social media","volume":"13","author":"Bouarara","year":"2021","journal-title":"International Journal of Software Science and Computational Intelligence (IJSSCI)"},{"unstructured":"J.\u00a0Liu, C.\u00a0Xu, C.\u00a0Yin, W.\u00a0Wu and Y.\u00a0Song, K-core based temporal graph convolutional network for dynamic graphs, IEEE Transactions on Knowledge and Data Engineering (2020).","key":"10.3233\/IDA-237367_ref10"},{"key":"10.3233\/IDA-237367_ref11","doi-asserted-by":"crossref","first-page":"107000","DOI":"10.1016\/j.patcog.2019.107000","article-title":"Dynamic graph convolutional networks","volume":"97","author":"Manessi","year":"2020","journal-title":"Pattern Recognition"},{"unstructured":"J.\u00a0Zhang, X.\u00a0Shi, J.\u00a0Xie, H.\u00a0Ma, I.\u00a0King and D.-Y.\u00a0Yeung, Gaan: Gated attention networks for learning on large and spatiotemporal graphs, arXiv preprint arXiv:1803.07294, (2018).","key":"10.3233\/IDA-237367_ref13"},{"key":"10.3233\/IDA-237367_ref14","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1145\/3336191.3371845","article-title":"Dysat: Deep neural representation learning on dynamic graphs via self-attention networks","author":"Sankar","year":"2020","journal-title":"Proceedings of the 13th international conference on web search and data mining"},{"key":"10.3233\/IDA-237367_ref15","first-page":"362","article-title":"Structured sequence modeling with graph convolutional recurrent networks","author":"Seo","year":"2018","journal-title":"International conference on neural information processing"},{"key":"10.3233\/IDA-237367_ref16","doi-asserted-by":"crossref","first-page":"5363","DOI":"10.1609\/aaai.v34i04.5984","article-title":"Evolvegcn: Evolving graph convolutional networks for dynamic graphs","author":"Pareja","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"unstructured":"Y.\u00a0Wang, M.\u00a0Long, J.\u00a0Wang, Z.\u00a0Gao and P.S.\u00a0Yu, Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms, Advances in Neural Information Processing Systems 30 (2017).","key":"10.3233\/IDA-237367_ref17"},{"doi-asserted-by":"crossref","unstructured":"J.\u00a0Chen, X.\u00a0Wang and X.\u00a0Xu, Gc-lstm: Graph convolution embedded lstm for dynamic link prediction, Applied Intelligence (2021).","key":"10.3233\/IDA-237367_ref18","DOI":"10.1007\/s10489-021-02518-9"},{"key":"10.3233\/IDA-237367_ref19","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018","journal-title":"European semantic web conference"},{"key":"10.3233\/IDA-237367_ref20","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1145\/3292500.3330847","article-title":"Predicting path failure in time-evolving graphs","author":"Li","year":"2019","journal-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"},{"key":"10.3233\/IDA-237367_ref22","doi-asserted-by":"crossref","first-page":"5336","DOI":"10.1109\/BigData47090.2019.9005545","article-title":"Temporal neighbourhood aggregation: Predicting future links in temporal graphs via recurrent variational graph convolutions","author":"Bonner","year":"2019","journal-title":"2019 IEEE international conference on big data (Big Data)"},{"issue":"6","key":"10.3233\/IDA-237367_ref25","doi-asserted-by":"crossref","first-page":"3699","DOI":"10.1109\/TSMC.2019.2932913","article-title":"E-lstm-d: A deep learning framework for dynamic network link prediction","volume":"51","author":"Chen","year":"2019","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"unstructured":"W.\u00a0Hamilton, Z.\u00a0Ying and J.\u00a0Leskovec, Inductive representation learning on large graphs, Advances in neural information processing systems 30 (2017).","key":"10.3233\/IDA-237367_ref26"},{"unstructured":"E.\u00a0Hajiramezanali, A.\u00a0Hasanzadeh, K.\u00a0Narayanan, N.\u00a0Duffield, M.\u00a0Zhou and X.\u00a0Qian, Variational graph recurrent neural networks, Advances in Neural Information Processing Systems 32 (2019).","key":"10.3233\/IDA-237367_ref27"},{"issue":"1","key":"10.3233\/IDA-237367_ref28","doi-asserted-by":"crossref","first-page":"173","DOI":"10.3233\/IDA-205524","article-title":"Temporal link prediction in directed networks based on self-attention mechanism","volume":"26","author":"Li","year":"2022","journal-title":"Intelligent Data Analysis"},{"issue":"1","key":"10.3233\/IDA-237367_ref29","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s00354-019-00065-z","article-title":"Temporal link prediction: A survey","volume":"38","author":"Divakaran","year":"2020","journal-title":"New Generation Computing"},{"issue":"4","key":"10.3233\/IDA-237367_ref30","first-page":"1440","article-title":"A Temporal Link Predict Algorithm Based on Fusion Local Structure Influence","volume":"44","author":"ZHU","year":"2022","journal-title":"Journal of Electronics & Information Technology"},{"unstructured":"A.\u00a0Vaswani, N.\u00a0Shazeer, N.\u00a0Parmar, J.\u00a0Uszkoreit, L.\u00a0Jones, A.N.\u00a0Gomez, \u0141.\u00a0Kaiser and I.\u00a0Polosukhin, Attention is all you need, Advances in neural Information Processing Systems 30 (2017).","key":"10.3233\/IDA-237367_ref31"},{"unstructured":"D.\u00a0Xu, C.\u00a0Ruan, E.\u00a0Korpeoglu, S.\u00a0Kumar and K.\u00a0Achan, Inductive representation learning on temporal graphs, arXiv preprint arXiv:2002.07962 (2020).","key":"10.3233\/IDA-237367_ref32"},{"key":"10.3233\/IDA-237367_ref33","first-page":"12026","article-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2019","journal-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"10.3233\/IDA-237367_ref34","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1145\/3018661.3018731","article-title":"Motifs in temporal networks","author":"Paranjape","year":"2017","journal-title":"Proceedings of the tenth ACM international conference on web search and data mining"},{"key":"10.3233\/IDA-237367_ref35","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1145\/2487788.2488173","article-title":"Konect: the koblenz network collection","author":"Kunegis","year":"2013","journal-title":"Proceedings of the 22nd international conference on world wide web"},{"doi-asserted-by":"crossref","unstructured":"R.\u00a0Rossi and N.\u00a0Ahmed, The network data repository with interactive graph analytics and visualization, in: Twenty-ninth AAAI conference on artificial intelligence, 2015.","key":"10.3233\/IDA-237367_ref37","DOI":"10.1609\/aaai.v29i1.9277"},{"key":"10.3233\/IDA-237367_ref38","doi-asserted-by":"crossref","first-page":"1361","DOI":"10.1145\/1753326.1753532","article-title":"Signed networks in social media","author":"Leskovec","year":"2010","journal-title":"Proceedings of the SIGCHI conference on human factors in computing systems"},{"doi-asserted-by":"crossref","unstructured":"B.\u00a0Yu, H.\u00a0Yin and Z.\u00a0Zhu, Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting, arXiv preprint arXiv:1709.04875 (2017).","key":"10.3233\/IDA-237367_ref39","DOI":"10.24963\/ijcai.2018\/505"},{"issue":"7","key":"10.3233\/IDA-237367_ref40","doi-asserted-by":"crossref","first-page":"485","DOI":"10.3390\/ijgi10070485","article-title":"A3t-gcn: Attention temporal graph convolutional network for traffic forecasting","volume":"10","author":"Bai","year":"2021","journal-title":"ISPRS International Journal of Geo-Information"},{"key":"10.3233\/IDA-237367_ref41","first-page":"57","article-title":"Predictive temporal embedding of dynamic graphs","author":"Taheri","year":"2019","journal-title":"Proceedings of the 2019 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining"},{"key":"10.3233\/IDA-237367_ref42","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1145\/3485447.3512164","article-title":"Trend: Temporal event and node dynamics for graph representation learning","author":"Wen","year":"2022","journal-title":"Proceedings of the ACM Web Conference 2022"},{"key":"10.3233\/IDA-237367_ref43","doi-asserted-by":"crossref","first-page":"108216","DOI":"10.1016\/j.patcog.2021.108216","article-title":"Joint multi-label learning and feature extraction for temporal link prediction","volume":"121","author":"Ma","year":"2022","journal-title":"Pattern Recognition"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-237367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T18:10:37Z","timestamp":1741630237000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-237367"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,3]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ida-237367","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"type":"print","value":"1088-467X"},{"type":"electronic","value":"1571-4128"}],"subject":[],"published":{"date-parts":[[2024,2,3]]}}}