{"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/gaussian-induced-convolution-for-graphs","title":"Gaussian-Induced Convolution for Graphs","arxiv_id":"1811.04393","date":"2018-11-11","proceeding":null,"authors":["Jiatao Jiang","Zhen Cui","Chunyan Xu","Jian Yang"],"abstract":"Learning representation on graph plays a crucial role in numerous tasks of\npattern recognition. Different from grid-shaped images/videos, on which local\nconvolution kernels can be lattices, however, graphs are fully coordinate-free\non vertices and edges. In this work, we propose a Gaussian-induced convolution\n(GIC) framework to conduct local convolution filtering on irregular graphs.\nSpecifically, an edge-induced Gaussian mixture model is designed to encode\nvariations of subgraph region by integrating edge information into weighted\nGaussian models, each of which implicitly characterizes one component of\nsubgraph variations. In order to coarsen a graph, we derive a vertex-induced\nGaussian mixture model to cluster vertices dynamically according to the\nconnection of edges, which is approximately equivalent to the weighted graph\ncut. We conduct our multi-layer graph convolution network on several public\ndatasets of graph classification. The extensive experiments demonstrate that\nour GIC is effective and can achieve the state-of-the-art results.","url_abs":"http://arxiv.org/abs/1811.04393v1","url_pdf":"http://arxiv.org/pdf/1811.04393v1.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":[],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"learning-representation-on-graph","task_name":"Learning Representation On Graph"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"GIC","rank_in_archive_order":26,"of":54,"metrics":{"Accuracy":"62.50%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"GIC","rank_in_archive_order":6,"of":74,"metrics":{"Accuracy":"94.44%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"GIC","rank_in_archive_order":23,"of":69,"metrics":{"Accuracy":"84.08%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci109","task":"Graph Classification","dataset":"NCI109","model":"GIC","rank_in_archive_order":15,"of":38,"metrics":{"Accuracy":"82.86"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"GIC","rank_in_archive_order":30,"of":103,"metrics":{"Accuracy":"77.65%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"GIC","rank_in_archive_order":3,"of":37,"metrics":{"Accuracy":"77.64%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}