{"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/apan-asynchronous-propagate-attention-network","title":"APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding","arxiv_id":"2011.11545","date":"2020-11-23","proceeding":null,"authors":["Xuhong Wang","Ding Lyu","Mengjian Li","Yang Xia","Qi Yang","Xinwen Wang","Xinguang Wang","Ping Cui","Yupu Yang","Bowen Sun","Zhenyu Guo"],"abstract":"Limited by the time complexity of querying k-hop neighbors in a graph database, most graph algorithms cannot be deployed online and execute millisecond-level inference. This problem dramatically limits the potential of applying graph algorithms in certain areas, such as financial fraud detection. Therefore, we propose Asynchronous Propagation Attention Network, an asynchronous continuous time dynamic graph algorithm for real-time temporal graph embedding. Traditional graph models usually execute two serial operations: first graph computation and then model inference. We decouple model inference and graph computation step so that the heavy graph query operations will not damage the speed of model inference. Extensive experiments demonstrate that the proposed method can achieve competitive performance and 8.7 times inference speed improvement in the meantime.","url_abs":"https://arxiv.org/abs/2011.11545v4","url_pdf":"https://arxiv.org/pdf/2011.11545v4.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":"apan-asynchronous-propagate-attention-network","repo_url":"https://github.com/doujiang-zheng/dynamic-preference-structure","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"fraud-detection","task_name":"Fraud Detection"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.11545","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}