{"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/active-learning-for-graph-embedding","title":"Active Learning for Graph Embedding","arxiv_id":"1705.05085","date":"2017-05-15","proceeding":null,"authors":["Hongyun Cai","Vincent W. Zheng","Kevin Chen-Chuan Chang"],"abstract":"Graph embedding provides an efficient solution for graph analysis by\nconverting the graph into a low-dimensional space which preserves the structure\ninformation. In contrast to the graph structure data, the i.i.d. node embedding\ncan be processed efficiently in terms of both time and space. Current\nsemi-supervised graph embedding algorithms assume the labelled nodes are given,\nwhich may not be always true in the real world. While manually label all\ntraining data is inapplicable, how to select the subset of training data to\nlabel so as to maximize the graph analysis task performance is of great\nimportance. This motivates our proposed active graph embedding (AGE) framework,\nin which we design a general active learning query strategy for any\nsemi-supervised graph embedding algorithm. AGE selects the most informative\nnodes as the training labelled nodes based on the graphical information (i.e.,\nnode centrality) as well as the learnt node embedding (i.e., node\nclassification uncertainty and node embedding representativeness). Different\nquery criteria are combined with the time-sensitive parameters which shift the\nfocus from graph based query criteria to embedding based criteria as the\nlearning progresses. Experiments have been conducted on three public data sets\nand the results verified the effectiveness of each component of our query\nstrategy and the power of combining them using time-sensitive parameters. Our\ncode is available online at: https://github.com/vwz/AGE.","url_abs":"http://arxiv.org/abs/1705.05085v1","url_pdf":"http://arxiv.org/pdf/1705.05085v1.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":"active-learning-for-graph-embedding","repo_url":"https://github.com/vwz/AGE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.05085","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}