{"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/clique-pooling-for-graph-classification","title":"Clique pooling for graph classification","arxiv_id":"1904.00374","date":"2019-03-31","proceeding":null,"authors":["Enxhell Luzhnica","Ben Day","Pietro Lio'"],"abstract":"We propose a novel graph pooling operation using cliques as the unit pool. As\nthis approach is purely topological, rather than featural, it is more readily\ninterpretable, a better analogue to image coarsening than filtering or pruning\ntechniques, and entirely nonparametric. The operation is implemented within\ngraph convolution network (GCN) and GraphSAGE architectures and tested against\nstandard graph classification benchmarks. In addition, we explore the backwards\ncompatibility of the pooling to regular graphs, demonstrating competitive\nperformance when replacing two-by-two pooling in standard convolutional neural\nnetworks (CNNs) with our mechanism.","url_abs":"http://arxiv.org/abs/1904.00374v2","url_pdf":"http://arxiv.org/pdf/1904.00374v2.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":"clique-pooling-for-graph-classification","repo_url":"https://gitlab.com/cedric_sanders/masterarbeit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"graphsage","method_name":"GraphSAGE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00374","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}