{"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/message-passing-graph-kernels","title":"Message Passing Graph Kernels","arxiv_id":"1808.02510","date":"2018-08-07","proceeding":null,"authors":["Giannis Nikolentzos","Michalis Vazirgiannis"],"abstract":"Graph kernels have recently emerged as a promising approach for tackling the\ngraph similarity and learning tasks at the same time. In this paper, we propose\na general framework for designing graph kernels. The proposed framework\ncapitalizes on the well-known message passing scheme on graphs. The kernels\nderived from the framework consist of two components. The first component is a\nkernel between vertices, while the second component is a kernel between graphs.\nThe main idea behind the proposed framework is that the representations of the\nvertices are implicitly updated using an iterative procedure. Then, these\nrepresentations serve as the building blocks of a kernel that compares pairs of\ngraphs. We derive four instances of the proposed framework, and show through\nextensive experiments that these instances are competitive with\nstate-of-the-art methods in various tasks.","url_abs":"http://arxiv.org/abs/1808.02510v1","url_pdf":"http://arxiv.org/pdf/1808.02510v1.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":"message-passing-graph-kernels","repo_url":"https://github.com/giannisnik/message_passing_graph_kernels","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"graph-similarity","task_name":"Graph Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.02510","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}