{"id":13628240,"url":"https://github.com/Eilene/GWNN","last_synced_at":"2025-04-17T00:33:55.745Z","repository":{"id":88915275,"uuid":"167883355","full_name":"Eilene/GWNN","owner":"Eilene","description":" A TensorFlow implementation of Graph Wavelet Neural Network","archived":false,"fork":false,"pushed_at":"2019-01-28T15:01:17.000Z","size":5872,"stargazers_count":63,"open_issues_count":6,"forks_count":18,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-08-01T22:42:05.569Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Eilene.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-01-28T02:02:44.000Z","updated_at":"2024-05-15T03:44:38.000Z","dependencies_parsed_at":"2023-06-13T03:00:18.420Z","dependency_job_id":null,"html_url":"https://github.com/Eilene/GWNN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eilene%2FGWNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eilene%2FGWNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eilene%2FGWNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Eilene%2FGWNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Eilene","download_url":"https://codeload.github.com/Eilene/GWNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223735384,"owners_count":17194092,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T22:00:48.984Z","updated_at":"2024-11-08T18:31:41.764Z","avatar_url":"https://github.com/Eilene.png","language":"Python","funding_links":[],"categories":["Uncategorized"],"sub_categories":["Uncategorized"],"readme":"## Graph Wavelet Neural Network\n\u003e Graph Wavelet Neural Network. Bingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, Xueqi Cheng. ICLR, 2019. [pdf](https://openreview.net/pdf?id=H1ewdiR5tQ)\n\n## Overview\n\n\u003cdiv align=center\u003e\n \u003cimg src=\"wavelet_basis.jpeg\" alt=\"Wavelet_basis\" align=center/\u003e\n\u003c/div\u003e\n\n\u003e We provide a TensorFlow implementation of Graph Wavelet Neural Network, which implements graph convolution via graph wavelet transform instead of Fourier transform. Different from graph Fourier transform, graph wavelets are sparse and localized in vertex domain, offering high efficiency and good interpretability for graph convolution. We evaluated our model in the task of graph-based semi-supervised classification.\n\n## Requirements\nthe script has been tested running under Python 2.7, with the following packages installed (along with their dependencies):\n* tensorflow==0.12.0\n* numpy==1.14.0\n* scipy==0.19.1\n* networkx==2.0\n\n## Run the Code\n* cd GraphWaveletNetwork\n* python train.py\n\n## Parameters\n* --wavelet_s                 FLOAT         wavelet scaling parameter.                  Default: Cora: 1.0, Citeseer: 0.7, Pubmed: 0.5\n* --threshold                 FLOAT         threshold parameter for wavelet.            Default: Cora: 1e-4, Citeseer: 1e-5, Pubmed: 1e-7\n* --epochs                    INT           Number of Adam epochs.                      Default: 1000.\n* --early-stopping            INT           Number of early stopping epochs.            Default: 100.\n\n## Run Example\nThe run example for Cora dataset in default parameter\n\u003cdiv align=center\u003e\n \u003cimg src=\"cora_run.jpeg\" alt=\"cora_accuracy\" align=center/\u003e\n\u003c/div\u003e\n\n## Cite\nPlease cite our paper if you use this code in your own work:\n\n\u003e @inproceedings{\nxu2018graph,\ntitle={Graph Wavelet Neural Network},\nauthor={Bingbing Xu and Huawei Shen and Qi Cao and Yunqi Qiu and Xueqi Cheng},\nbooktitle={International Conference on Learning Representations},\nyear={2019},\nurl={https://openreview.net/forum?id=H1ewdiR5tQ},\n}\n\n## Acknowledgement\n\n\u003e Some sections of code adapted from tkipf/gcn(https://github.com/tkipf/gcn)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEilene%2FGWNN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEilene%2FGWNN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEilene%2FGWNN/lists"}