{"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/temporal-graph-offset-reconstruction-towards","title":"Temporal Graph Offset Reconstruction: Towards Temporally Robust Graph Representation Learning","arxiv_id":"1811.08366","date":"2018-11-20","proceeding":null,"authors":["Stephen Bonner","John Brennan","Ibad Kureshi","Georgios Theodoropoulos","Andrew Stephen McGough","Boguslaw Obara"],"abstract":"Graphs are a commonly used construct for representing relationships between\nelements in complex high dimensional datasets. Many real-world phenomenon are\ndynamic in nature, meaning that any graph used to represent them is inherently\ntemporal. However, many of the machine learning models designed to capture\nknowledge about the structure of these graphs ignore this rich temporal\ninformation when creating representations of the graph. This results in models\nwhich do not perform well when used to make predictions about the future state\nof the graph -- especially when the delta between time stamps is not small. In\nthis work, we explore a novel training procedure and an associated unsupervised\nmodel which creates graph representations optimised to predict the future state\nof the graph. We make use of graph convolutional neural networks to encode the\ngraph into a latent representation, which we then use to train our temporal\noffset reconstruction method, inspired by auto-encoders, to predict a later\ntime point -- multiple time steps into the future. Using our method, we\ndemonstrate superior performance for the task of future link prediction\ncompared with none-temporal state-of-the-art baselines. We show our approach to\nbe capable of outperforming non-temporal baselines by 38% on a real world\ndataset.","url_abs":"http://arxiv.org/abs/1811.08366v1","url_pdf":"http://arxiv.org/pdf/1811.08366v1.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":"temporal-graph-offset-reconstruction-towards","repo_url":"https://github.com/sbonner0/temporal-offset-reconstruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}