{"id":13444151,"url":"https://github.com/lightaime/deep_gcns_torch","last_synced_at":"2025-05-16T11:04:10.969Z","repository":{"id":38360247,"uuid":"199716757","full_name":"lightaime/deep_gcns_torch","owner":"lightaime","description":"Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org","archived":false,"fork":false,"pushed_at":"2022-07-31T21:01:32.000Z","size":7362,"stargazers_count":1158,"open_issues_count":6,"forks_count":155,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-04-09T06:07:31.360Z","etag":null,"topics":["3d-point-clouds","bioinformatics","cheminformatics","computer-vision","data-mining","deep-gcns","deep-learning","geometric-deep-learning","graph-convolutional-networks","graph-neural-networks","pytorch","science-research","social-network"],"latest_commit_sha":null,"homepage":"","language":"Python","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/lightaime.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}},"created_at":"2019-07-30T19:44:00.000Z","updated_at":"2025-04-08T09:15:48.000Z","dependencies_parsed_at":"2022-07-12T17:27:41.719Z","dependency_job_id":null,"html_url":"https://github.com/lightaime/deep_gcns_torch","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/lightaime%2Fdeep_gcns_torch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightaime%2Fdeep_gcns_torch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightaime%2Fdeep_gcns_torch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lightaime%2Fdeep_gcns_torch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lightaime","download_url":"https://codeload.github.com/lightaime/deep_gcns_torch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254518384,"owners_count":22084374,"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":["3d-point-clouds","bioinformatics","cheminformatics","computer-vision","data-mining","deep-gcns","deep-learning","geometric-deep-learning","graph-convolutional-networks","graph-neural-networks","pytorch","science-research","social-network"],"created_at":"2024-07-31T03:02:20.370Z","updated_at":"2025-05-16T11:04:10.948Z","avatar_url":"https://github.com/lightaime.png","language":"Python","funding_links":[],"categories":["Python","图卷积网络"],"sub_categories":["资源传输下载"],"readme":"# DeepGCNs: Can GCNs Go as Deep as CNNs?\nIn this work, we present new ways to successfully train very deep GCNs. We borrow concepts from CNNs, mainly residual/dense connections and dilated convolutions, and adapt them to GCN architectures. Through extensive experiments, we show the positive effect of these deep GCN frameworks.\n\n[[Project]](https://www.deepgcns.org/) [[Paper]](https://arxiv.org/abs/1904.03751) [[Slides]](https://docs.google.com/presentation/d/1L82wWymMnHyYJk3xUKvteEWD5fX0jVRbCbI65Cxxku0/edit?usp=sharing) [[Tensorflow Code]](https://github.com/lightaime/deep_gcns) [[Pytorch Code]](https://github.com/lightaime/deep_gcns_torch)\n    \n\u003cp align=\"center\"\u003e\n  \u003cimg src='./misc/intro.png' width=800\u003e\n\u003c/p\u003e\n\n## Overview\nWe do extensive experiments to show how different components (#Layers, #Filters, #Nearest Neighbors, Dilation, etc.) effect `DeepGCNs`. We also provide ablation studies on different type of Deep GCNs (MRGCN, EdgeConv, GraphSage and GIN).\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src='./misc/pipeline.png' width=800\u003e\n\u003c/p\u003e\n\n\n## How to train, test and evaluate our models\nPlease look the details in `Readme.md` of each task inside `examples` folder.\nAll the information of code, data, and pretrained models can be found there.\n* DeepGCNs ([ICCV'2019](https://arxiv.org/abs/1904.03751), [TPAMI'2021](https://arxiv.org/abs/1910.06849)): [S3DIS](examples/sem_seg_dense), [PartNet](examples/part_sem_seg), [ModelNet40](examples/modelnet_cls), [PPI](/examples/ppi)\n* DeeperGCN ([Arxiv'2020](https://arxiv.org/abs/2006.07739)): [OGB](examples/ogb)\n* GNN'1000 ([ICML'2021](https://arxiv.org/abs/2106.07476)): [OGB](examples/ogb_eff)\n\n## Recommended Requirements\n* [Python\u003e=3.7](https://www.python.org/)\n* [Pytorch\u003e=1.9.0](https://pytorch.org)\n* [pytorch_geometric\u003e=1.6.0](https://pytorch-geometric.readthedocs.io/en/latest/)\n* [ogb\u003e=1.3.1](https://github.com/snap-stanford/ogb) only used for experiments on OGB datasets\n* [dgl\u003e=0.5.3](https://github.com/dmlc/dgl) only used for the experiment `examples/ogb_eff/ogbn_arxiv_dgl`\n\nInstall enviroment by runing:\n```\nsource deepgcn_env_install.sh\n```\n\n## Code Architecture\n    .\n    ├── misc                    # Misc images\n    ├── utils                   # Common useful modules\n    ├── gcn_lib                 # gcn library\n    │   ├── dense               # gcn library for dense data (B x C x N x 1)\n    │   └── sparse              # gcn library for sparse data (N x C)\n    ├── eff_gcn_modules         # modules for mem efficient gnns\n    ├── examples \n    │   ├── modelnet_cls        # code for point clouds classification on ModelNet40\n    │   ├── sem_seg_dense       # code for point clouds semantic segmentation on S3DIS (data type: dense)\n    │   ├── sem_seg_sparse      # code for point clouds semantic segmentation on S3DIS (data type: sparse)\n    │   ├── part_sem_seg        # code for part segmentation on PartNet\n    │   ├── ppi                 # code for node classification on PPI dataset\n    │   └── ogb                 # code for node/graph property prediction on OGB datasets\n    │   └── ogb_eff             # code for node/graph property prediction on OGB datasets with memory efficient GNNs\n    └── ...\n\n## Citation\nPlease cite our paper if you find anything helpful,\n\n```\n@InProceedings{li2019deepgcns,\n    title={DeepGCNs: Can GCNs Go as Deep as CNNs?},\n    author={Guohao Li and Matthias Müller and Ali Thabet and Bernard Ghanem},\n    booktitle={The IEEE International Conference on Computer Vision (ICCV)},\n    year={2019}\n}\n```\n\n```\n@article{li2021deepgcns_pami,\n  title={Deepgcns: Making gcns go as deep as cnns},\n  author={Li, Guohao and M{\\\"u}ller, Matthias and Qian, Guocheng and Perez, Itzel Carolina Delgadillo and Abualshour, Abdulellah and Thabet, Ali Kassem and Ghanem, Bernard},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},\n  year={2021},\n  publisher={IEEE}\n}\n```\n\n```\n@misc{li2020deepergcn,\n    title={DeeperGCN: All You Need to Train Deeper GCNs},\n    author={Guohao Li and Chenxin Xiong and Ali Thabet and Bernard Ghanem},\n    year={2020},\n    eprint={2006.07739},\n    archivePrefix={arXiv},\n    primaryClass={cs.LG}\n}\n```\n\n```\n@InProceedings{li2021gnn1000,\n    title={Training Graph Neural Networks with 1000 layers},\n    author={Guohao Li and Matthias Müller and Bernard Ghanem and Vladlen Koltun},\n    booktitle={International Conference on Machine Learning (ICML)},\n    year={2021}\n}\n```\n\n## License\nMIT License\n\n## Contact\nFor more information please contact [Guohao Li](https://ghli.org), [Matthias Muller](https://matthias.pw/), [Guocheng Qian](https://www.gcqian.com/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightaime%2Fdeep_gcns_torch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flightaime%2Fdeep_gcns_torch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightaime%2Fdeep_gcns_torch/lists"}