{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/e-lstm-d-a-deep-learning-framework-for","title":"E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction","arxiv_id":"1902.08329","date":"2019-02-22","proceeding":null,"authors":["Jinyin Chen","Jian Zhang","Xuanheng Xu","Chengbo Fu","Dan Zhang","Qingpeng Zhang","Qi Xuan"],"abstract":"Predicting the potential relations between nodes in networks, known as link\nprediction, has long been a challenge in network science. However, most studies\njust focused on link prediction of static network, while real-world networks\nalways evolve over time with the occurrence and vanishing of nodes and links.\nDynamic network link prediction thus has been attracting more and more\nattention since it can better capture the evolution nature of networks, but\nstill most algorithms fail to achieve satisfied prediction accuracy. Motivated\nby the excellent performance of Long Short-Term Memory (LSTM) in processing\ntime series, in this paper, we propose a novel Encoder-LSTM-Decoder (E-LSTM-D)\ndeep learning model to predict dynamic links end to end. It could handle long\nterm prediction problems, and suits the networks of different scales with\nfine-tuned structure. To the best of our knowledge, it is the first time that\nLSTM, together with an encoder-decoder architecture, is applied to link\nprediction in dynamic networks. This new model is able to automatically learn\nstructural and temporal features in a unified framework, which can predict the\nlinks that never appear in the network before. The extensive experiments show\nthat our E-LSTM-D model significantly outperforms newly proposed dynamic\nnetwork link prediction methods and obtain the state-of-the-art results.","url_abs":"http://arxiv.org/abs/1902.08329v1","url_pdf":"http://arxiv.org/pdf/1902.08329v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"e-lstm-d-a-deep-learning-framework-for","repo_url":"https://github.com/jianz94/e-lstm-d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.08329","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}