{"id":13481257,"url":"https://github.com/xbresson/spatial_graph_convnets","last_synced_at":"2025-03-27T11:32:11.845Z","repository":{"id":169210131,"uuid":"130803418","full_name":"xbresson/spatial_graph_convnets","owner":"xbresson","description":"PyTorch implementation of residual gated graph ConvNets, ICLR’18","archived":false,"fork":false,"pushed_at":"2018-10-24T09:10:20.000Z","size":4304,"stargazers_count":121,"open_issues_count":0,"forks_count":34,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-08-01T17:25:41.144Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xbresson.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2018-04-24T05:56:57.000Z","updated_at":"2024-07-07T19:23:41.000Z","dependencies_parsed_at":null,"dependency_job_id":"cf23275a-5b33-42f1-850d-a93a9d29d2d7","html_url":"https://github.com/xbresson/spatial_graph_convnets","commit_stats":null,"previous_names":["xbresson/spatial_graph_convnets"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xbresson%2Fspatial_graph_convnets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xbresson%2Fspatial_graph_convnets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xbresson%2Fspatial_graph_convnets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xbresson%2Fspatial_graph_convnets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xbresson","download_url":"https://codeload.github.com/xbresson/spatial_graph_convnets/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":222239550,"owners_count":16953974,"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":"2024-07-31T17:00:50.201Z","updated_at":"2024-10-30T14:31:26.183Z","avatar_url":"https://github.com/xbresson.png","language":"Jupyter Notebook","funding_links":[],"categories":["Deep Learning"],"sub_categories":[],"readme":"# Residual Gated Graph ConvNets\nApril 24, 2018\n\u003cbr\u003e\n\u003cbr\u003e\n\n\n\n\u003cimg src=\"pic/subgraph_matching.jpg\" align=\"right\" width=\"300\"/\u003e\n\n\n### Xavier Bresson\n\u003cimg src=\"pic/home100.jpg\" width=\"15\" height=\"15\"/\u003e http://www.ntu.edu.sg/home/xbresson\u003cbr\u003e\n\u003cimg src=\"pic/github100.jpg\" width=\"15\" height=\"15\"/\u003e https://github.com/xbresson\u003cbr\u003e\n\u003cimg src=\"pic/twitter100.jpg\" width=\"15\" height=\"15\"/\u003e https://twitter.com/xbresson \u003cbr\u003e\n\u003cimg src=\"pic/facebook100.jpg\" width=\"15\" height=\"15\"/\u003e https://www.facebook.com/xavier.bresson.1 \u003cbr\u003e\n\u003cbr\u003e\n\n\n### Description\nPrototype implementation in PyTorch of the ICLR'18 paper:\u003cbr\u003e\nAn Experimental Study of Neural Networks for Variable Graphs\u003cbr\u003e\nXavier Bresson and Thomas Laurent\u003cbr\u003e\nInternational Conference on Learning Representations, 2018\u003cbr\u003e\nICLR OpenReview: https://openreview.net/pdf?id=SJexcZc8G\u003cbr\u003e\nArXiv extended version: [arXiv:1711.07553](https://arxiv.org/pdf/1711.07553v2.pdf) \u003cbr\u003e\n[ICLR Poster] \u003cbr\u003e\n\u003cbr\u003e\n\n[ICLR Poster]: poster/poster_ICLR18.pdf\n\n\n### Codes\nThe code `01_residual_gated_graph_convnets_subgraph_matching.ipynb` presents an application of the residual gated graph convNets for the problem of sub-graph matching.\u003cbr\u003e\nThe code `02_residual_gated_graph_convnets_semisupervised_clustering.ipynb` shows another application for the problem of semi-supervised_clustering.\u003cbr\u003e\n\u003cbr\u003e\n\n\n### Installation\n   ```sh\n   # Conda installation\n   curl -o ~/miniconda.sh -O https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh # Linux\n   curl -o ~/miniconda.sh -O https://repo.continuum.io/miniconda/Miniconda3-latest-MacOSX-x86_64.sh # OSX\n   chmod +x ~/miniconda.sh\n   ./miniconda.sh\n   source ~/.bashrc\n\n   # Clone GitHub repo\n   git clone https://github.com/xbresson/spatial_graph_convnets.git\n   cd spatial_graph_convnets\n\n   # Install python libraries\n   conda env create -f environment.yml\n   conda activate graph_convnets\n\n   # Run the 2 notebooks\n   jupyter notebook\n   ```\n\u003cbr\u003e\n\n\n\n### Results\nGeForce GTX 1080Ti\u003cbr\u003e\n* Sub-graph matching: **01_residual_gated_graph_convnets_subgraph_matching.ipynb**, accuracy= 98.85. \u003cbr\u003e\n* Semi-supervised_clustering: **02_residual_gated_graph_convnets_semisupervised_clustering.ipynb**, accuracy= 75.88. \u003cbr\u003e\n\u003cbr\u003e\n\n\n\n\n### When to use this algorithm?\nAny problem that can be cast as analyzing a set of graphs with variable size and connectivity, and one wants to use ConvNets for this analysis.\u003cbr\u003e\n\u003cbr\u003e\n\n\u003cbr\u003e\n\u003cbr\u003e\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxbresson%2Fspatial_graph_convnets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxbresson%2Fspatial_graph_convnets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxbresson%2Fspatial_graph_convnets/lists"}