{"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/models-for-capturing-temporal-smoothness-in","title":"Models for Capturing Temporal Smoothness in Evolving Networks for Learning Latent Representation of Nodes","arxiv_id":"1804.05816","date":"2018-04-16","proceeding":null,"authors":["Tanay Kumar Saha","Thomas Williams","Mohammad Al Hasan","Shafiq Joty","Nicholas K. Varberg"],"abstract":"In a dynamic network, the neighborhood of the vertices evolve across\ndifferent temporal snapshots of the network. Accurate modeling of this temporal\nevolution can help solve complex tasks involving real-life social and\ninteraction networks. However, existing models for learning latent\nrepresentation are inadequate for obtaining the representation vectors of the\nvertices for different time-stamps of a dynamic network in a meaningful way. In\nthis paper, we propose latent representation learning models for dynamic\nnetworks which overcome the above limitation by considering two different kinds\nof temporal smoothness: (i) retrofitted, and (ii) linear transformation. The\nretrofitted model tracks the representation vector of a vertex over time,\nfacilitating vertex-based temporal analysis of a network. On the other hand,\nlinear transformation based model provides a smooth transition operator which\nmaps the representation vectors of all vertices from one temporal snapshot to\nthe next (unobserved) snapshot-this facilitates prediction of the state of a\nnetwork in a future time-stamp. We validate the performance of our proposed\nmodels by employing them for solving the temporal link prediction task.\nExperiments on 9 real-life networks from various domains validate that the\nproposed models are significantly better than the existing models for\npredicting the dynamics of an evolving network.","url_abs":"http://arxiv.org/abs/1804.05816v1","url_pdf":"http://arxiv.org/pdf/1804.05816v1.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":"models-for-capturing-temporal-smoothness-in","repo_url":"https://gitlab.com/tksaha/temporalnode2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05816","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}