{"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/graph-wavelet-neural-network-1","title":"Graph Wavelet Neural Network","arxiv_id":"1904.07785","date":"2019-04-12","proceeding":"ICLR 2019 5","authors":["Bingbing Xu","Hua-Wei Shen","Qi Cao","Yunqi Qiu","Xue-Qi Cheng"],"abstract":"We present graph wavelet neural network (GWNN), a novel graph convolutional\nneural network (CNN), leveraging graph wavelet transform to address the\nshortcomings of previous spectral graph CNN methods that depend on graph\nFourier transform. Different from graph Fourier transform, graph wavelet\ntransform can be obtained via a fast algorithm without requiring matrix\neigendecomposition with high computational cost. Moreover, graph wavelets are\nsparse and localized in vertex domain, offering high efficiency and good\ninterpretability for graph convolution. The proposed GWNN significantly\noutperforms previous spectral graph CNNs in the task of graph-based\nsemi-supervised classification on three benchmark datasets: Cora, Citeseer and\nPubmed.","url_abs":"http://arxiv.org/abs/1904.07785v1","url_pdf":"http://arxiv.org/pdf/1904.07785v1.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":"graph-wavelet-neural-network-1","repo_url":"https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"GWNN","rank_in_archive_order":51,"of":71,"metrics":{"Accuracy":"71.7%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"GWNN","rank_in_archive_order":60,"of":73,"metrics":{"Accuracy":"81.6%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"GWNN","rank_in_archive_order":51,"of":70,"metrics":{"Accuracy":"79.1%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.07785","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}