{"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/fusion-graph-convolutional-networks","title":"Fusion Graph Convolutional Networks","arxiv_id":"1805.12528","date":"2018-05-31","proceeding":null,"authors":["Priyesh Vijayan","Yash Chandak","Mitesh M. Khapra","Srinivasan Parthasarathy","Balaraman Ravindran"],"abstract":"Semi-supervised node classification in attributed graphs, i.e., graphs with\nnode features, involves learning to classify unlabeled nodes given a partially\nlabeled graph. Label predictions are made by jointly modeling the node and its'\nneighborhood features. State-of-the-art models for node classification on such\nattributed graphs use differentiable recursive functions that enable\naggregation and filtering of neighborhood information from multiple hops. In\nthis work, we analyze the representation capacity of these models to regulate\ninformation from multiple hops independently. From our analysis, we conclude\nthat these models despite being powerful, have limited representation capacity\nto capture multi-hop neighborhood information effectively. Further, we also\npropose a mathematically motivated, yet simple extension to existing graph\nconvolutional networks (GCNs) which has improved representation capacity. We\nextensively evaluate the proposed model, F-GCN on eight popular datasets from\ndifferent domains. F-GCN outperforms the state-of-the-art models for\nsemi-supervised learning on six datasets while being extremely competitive on\nthe other two.","url_abs":"http://arxiv.org/abs/1805.12528v5","url_pdf":"http://arxiv.org/pdf/1805.12528v5.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":"fusion-graph-convolutional-networks","repo_url":"https://github.com/PriyeshV/FusionGCNs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}