{"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/stwalk-learning-trajectory-representations-in","title":"STWalk: Learning Trajectory Representations in Temporal Graphs","arxiv_id":"1711.04150","date":"2017-11-11","proceeding":null,"authors":["Supriya Pandhre","Himangi Mittal","Manish Gupta","Vineeth N. Balasubramanian"],"abstract":"Analyzing the temporal behavior of nodes in time-varying graphs is useful for\nmany applications such as targeted advertising, community evolution and outlier\ndetection. In this paper, we present a novel approach, STWalk, for learning\ntrajectory representations of nodes in temporal graphs. The proposed framework\nmakes use of structural properties of graphs at current and previous time-steps\nto learn effective node trajectory representations. STWalk performs random\nwalks on a graph at a given time step (called space-walk) as well as on graphs\nfrom past time-steps (called time-walk) to capture the spatio-temporal behavior\nof nodes. We propose two variants of STWalk to learn trajectory\nrepresentations. In one algorithm, we perform space-walk and time-walk as part\nof a single step. In the other variant, we perform space-walk and time-walk\nseparately and combine the learned representations to get the final trajectory\nembedding. Extensive experiments on three real-world temporal graph datasets\nvalidate the effectiveness of the learned representations when compared to\nthree baseline methods. We also show the goodness of the learned trajectory\nembeddings for change point detection, as well as demonstrate that arithmetic\noperations on these trajectory representations yield interesting and\ninterpretable results.","url_abs":"http://arxiv.org/abs/1711.04150v1","url_pdf":"http://arxiv.org/pdf/1711.04150v1.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":"stwalk-learning-trajectory-representations-in","repo_url":"https://github.com/supriya-pandhre/STWalk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"change-point-detection","task_name":"Change Point Detection"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}