{"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/exploring-the-role-of-node-diversity-in","title":"Exploring the Role of Node Diversity in Directed Graph Representation Learning","arxiv_id":null,"date":"2024-07-25","proceeding":"IJCAI 2024 7","authors":["Jincheng Huang","Yujie Mo","Ping Hu","Xiaoshuang Shi","Shangbo Yuan","Zeyu  Zhang","Xiaofeng Zhu"],"abstract":"Manymethods of Directed Graph Neural Networks\r\n (DGNNs) are designed to equally treat nodes in\r\n the same neighbor set (i.e., out-neighbor set and\r\n in-neighbor set) for every node, without consider\r\ning the node diversity in directed graphs, so they\r\n are often unavailable to adaptively acquire suitable\r\n information from neighbors of different directions.\r\n To alleviate this issue, in this paper, we investigate\r\n a new way to first consider node diversity for rep\r\nresentation learning on directed graphs, i.e., neigh\r\nbor diversity and degree diversity, and then propose\r\n a new NDDGNN framework to adaptively assign\r\n weights to both outgoing information and incom\r\ning information at the node level. Extensive ex\r\nperiments on seven real-world datasets validate the\r\n superior performance of our method compared to\r\n state-of-the-art methods in terms of both node clas\r\nsification and link prediction tasks.","url_abs":"https://www.ijcai.org/proceedings/2024/0229.pdf","url_pdf":"https://www.ijcai.org/proceedings/2024/0229.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":"exploring-the-role-of-node-diversity-in","repo_url":"https://github.com/huangJC0429/NDDGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}