{"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/streaming-graph-neural-networks","title":"Streaming Graph Neural Networks","arxiv_id":"1810.10627","date":"2018-10-24","proceeding":null,"authors":["Yao Ma","Ziyi Guo","Zhaochun Ren","Eric Zhao","Jiliang Tang","Dawei Yin"],"abstract":"Graphs are essential representations of many real-world data such as social\nnetworks. Recent years have witnessed the increasing efforts made to extend the\nneural network models to graph-structured data. These methods, which are\nusually known as the graph neural networks, have been applied to advance many\ngraphs related tasks such as reasoning dynamics of the physical system, graph\nclassification, and node classification. Most of the existing graph neural\nnetwork models have been designed for static graphs, while many real-world\ngraphs are inherently dynamic. For example, social networks are naturally\nevolving as new users joining and new relations being created. Current graph\nneural network models cannot utilize the dynamic information in dynamic graphs.\nHowever, the dynamic information has been proven to enhance the performance of\nmany graph analytic tasks such as community detection and link prediction.\nHence, it is necessary to design dedicated graph neural networks for dynamic\ngraphs. In this paper, we propose DGNN, a new {\\bf D}ynamic {\\bf G}raph {\\bf\nN}eural {\\bf N}etwork model, which can model the dynamic information as the\ngraph evolving. In particular, the proposed framework can keep updating node\ninformation by capturing the sequential information of edges (interactions),\nthe time intervals between edges and information propagation coherently.\nExperimental results on various dynamic graphs demonstrate the effectiveness of\nthe proposed framework.","url_abs":"http://arxiv.org/abs/1810.10627v2","url_pdf":"http://arxiv.org/pdf/1810.10627v2.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":"streaming-graph-neural-networks","repo_url":"https://github.com/alge24/DyGNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"streaming-graph-neural-networks","repo_url":"https://github.com/wyd1502/DGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"community-detection","task_name":"Community Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.10627","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}