{"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/on-filter-size-in-graph-convolutional","title":"On Filter Size in Graph Convolutional Networks","arxiv_id":"1811.10435","date":"2018-11-23","proceeding":null,"authors":["Dinh Van Tran","Nicolò Navarin","Alessandro Sperduti"],"abstract":"Recently, many researchers have been focusing on the definition of neural\nnetworks for graphs. The basic component for many of these approaches remains\nthe graph convolution idea proposed almost a decade ago. In this paper, we\nextend this basic component, following an intuition derived from the well-known\nconvolutional filters over multi-dimensional tensors. In particular, we derive\na simple, efficient and effective way to introduce a hyper-parameter on graph\nconvolutions that influences the filter size, i.e. its receptive field over the\nconsidered graph. We show with experimental results on real-world graph\ndatasets that the proposed graph convolutional filter improves the predictive\nperformance of Deep Graph Convolutional Networks.","url_abs":"http://arxiv.org/abs/1811.10435v1","url_pdf":"http://arxiv.org/pdf/1811.10435v1.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":"on-filter-size-in-graph-convolutional","repo_url":"https://github.com/dinhinfotech/PGC-DGCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"graph-convolutional-networks","method_name":"Graph Convolutional Networks"},{"method_slug":"pgc-dgcnn","method_name":"PGC-DGCNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10435","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}