{"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/efficient-representation-learning-using","title":"Efficient Representation Learning Using Random Walks for Dynamic Graphs","arxiv_id":"1901.01346","date":"2019-01-05","proceeding":null,"authors":["Hooman Peiro Sajjad","Andrew Docherty","Yuriy Tyshetskiy"],"abstract":"An important part of many machine learning workflows on graphs is vertex\nrepresentation learning, i.e., learning a low-dimensional vector representation\nfor each vertex in the graph. Recently, several powerful techniques for\nunsupervised representation learning have been demonstrated to give the\nstate-of-the-art performance in downstream tasks such as vertex classification\nand edge prediction. These techniques rely on random walks performed on the\ngraph in order to capture its structural properties. These structural\nproperties are then encoded in the vector representation space.\n  However, most contemporary representation learning methods only apply to\nstatic graphs while real-world graphs are often dynamic and change over time.\nStatic representation learning methods are not able to update the vector\nrepresentations when the graph changes; therefore, they must re-generate the\nvector representations on an updated static snapshot of the graph regardless of\nthe extent of the change in the graph. In this work, we propose computationally\nefficient algorithms for vertex representation learning that extend random walk\nbased methods to dynamic graphs. The computation complexity of our algorithms\ndepends upon the extent and rate of changes (the number of edges changed per\nupdate) and on the density of the graph. We empirically evaluate our algorithms\non real world datasets for downstream machine learning tasks of multi-class and\nmulti-label vertex classification. The results show that our algorithms can\nachieve competitive results to the state-of-the-art methods while being\ncomputationally efficient.","url_abs":"http://arxiv.org/abs/1901.01346v2","url_pdf":"http://arxiv.org/pdf/1901.01346v2.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":"efficient-representation-learning-using","repo_url":"https://github.com/shps/incremental-representation-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.01346","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}