{"id":13440277,"url":"https://github.com/mdeff/cnn_graph","last_synced_at":"2025-05-16T10:05:39.658Z","repository":{"id":37359675,"uuid":"68138233","full_name":"mdeff/cnn_graph","owner":"mdeff","description":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","archived":false,"fork":false,"pushed_at":"2020-06-13T21:47:49.000Z","size":362,"stargazers_count":1358,"open_issues_count":20,"forks_count":390,"subscribers_count":43,"default_branch":"master","last_synced_at":"2025-05-16T10:04:13.163Z","etag":null,"topics":["convolutional-neural-networks","deep-learning","graph-neural-networks","graph-signal-processing","graphs"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1606.09375","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/mdeff.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-09-13T18:59:32.000Z","updated_at":"2025-05-13T16:37:58.000Z","dependencies_parsed_at":"2022-07-13T15:59:20.245Z","dependency_job_id":null,"html_url":"https://github.com/mdeff/cnn_graph","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/mdeff%2Fcnn_graph","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdeff%2Fcnn_graph/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdeff%2Fcnn_graph/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mdeff%2Fcnn_graph/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mdeff","download_url":"https://codeload.github.com/mdeff/cnn_graph/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254509476,"owners_count":22082891,"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":["convolutional-neural-networks","deep-learning","graph-neural-networks","graph-signal-processing","graphs"],"created_at":"2024-07-31T03:01:21.270Z","updated_at":"2025-05-16T10:05:39.631Z","avatar_url":"https://github.com/mdeff.png","language":"Jupyter Notebook","funding_links":[],"categories":["Graph Embedding","Jupyter Notebook","Articles","TensorFlow Implementations","图卷积网络","Uncategorized"],"sub_categories":["网络服务_其他","Uncategorized"],"readme":"# Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering\n\nThe code in this repository implements an efficient generalization of the\npopular Convolutional Neural Networks (CNNs) to arbitrary graphs, presented in\nour paper:\n\nMichaël Defferrard, Xavier Bresson, Pierre Vandergheynst, [Convolutional Neural\nNetworks on Graphs with Fast Localized Spectral Filtering][arXiv], Neural\nInformation Processing Systems (NIPS), 2016.\n\nAdditional material:\n* [NIPS2016 spotlight video][video], 2016-11-22.\n* [Deep Learning on Graphs][slides_ntds], a lecture for EPFL's master course [A\n  Network Tour of Data Science][ntds], 2016-12-21.\n* [Deep Learning on Graphs][slides_dlid], an invited talk at the [Deep Learning on\n  Irregular Domains][dlid] workshop of BMVC, 2017-09-17.\n\n[video]: https://www.youtube.com/watch?v=cIA_m7vwOVQ\n[slides_ntds]: https://doi.org/10.6084/m9.figshare.4491686\n[ntds]: https://github.com/mdeff/ntds_2016\n[slides_dlid]: https://doi.org/10.6084/m9.figshare.5394805\n[dlid]: http://dlid.swansea.ac.uk\n\nThere is also implementations of the filters used in:\n* Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun, [Spectral Networks\n  and Locally Connected Networks on Graphs][bruna], International Conference on\n  Learning Representations (ICLR), 2014.\n* Mikael Henaff, Joan Bruna and Yann LeCun, [Deep Convolutional Networks on\n  Graph-Structured Data][henaff], arXiv, 2015.\n\n[arXiv]:  https://arxiv.org/abs/1606.09375\n[bruna]:  https://arxiv.org/abs/1312.6203\n[henaff]: https://arxiv.org/abs/1506.05163\n\n## Installation\n\n1. Clone this repository.\n   ```sh\n   git clone https://github.com/mdeff/cnn_graph\n   cd cnn_graph\n   ```\n\n2. Install the dependencies. The code should run with TensorFlow 1.0 and newer.\n   ```sh\n   pip install -r requirements.txt  # or make install\n   ```\n\n3. Play with the Jupyter notebooks.\n   ```sh\n   jupyter notebook\n   ```\n\n## Reproducing our results\n\nRun all the notebooks to reproduce the experiments on\n[MNIST](nips2016/mnist.ipynb) and [20NEWS](nips2016/20news.ipynb) presented in\nthe paper.\n```sh\ncd nips2016\nmake\n```\n\n## Using the model\n\nTo use our graph ConvNet on your data, you need:\n\n1. a data matrix where each row is a sample and each column is a feature,\n2. a target vector,\n3. optionally, an adjacency matrix which encodes the structure as a graph.\n\nSee the [usage notebook][usage] for a simple example with fabricated data.\nPlease get in touch if you are unsure about applying the model to a different\nsetting.\n\n[usage]: http://nbviewer.jupyter.org/github/mdeff/cnn_graph/blob/outputs/usage.ipynb\n\n## License \u0026 co\n\nThe code in this repository is released under the terms of the [MIT license](LICENSE.txt).\nPlease cite our [paper][arXiv] if you use it.\n\n```\n@inproceedings{cnn_graph,\n  title = {Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering},\n  author = {Defferrard, Micha\\\"el and Bresson, Xavier and Vandergheynst, Pierre},\n  booktitle = {Advances in Neural Information Processing Systems},\n  year = {2016},\n  url = {https://arxiv.org/abs/1606.09375},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmdeff%2Fcnn_graph","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmdeff%2Fcnn_graph","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmdeff%2Fcnn_graph/lists"}