{"id":13429437,"url":"https://github.com/graphdeeplearning/benchmarking-gnns","last_synced_at":"2025-05-15T07:06:22.091Z","repository":{"id":38337839,"uuid":"244534808","full_name":"graphdeeplearning/benchmarking-gnns","owner":"graphdeeplearning","description":"Repository for benchmarking graph neural networks (JMLR 2023)","archived":false,"fork":false,"pushed_at":"2023-06-22T04:03:53.000Z","size":3364,"stargazers_count":2578,"open_issues_count":8,"forks_count":455,"subscribers_count":58,"default_branch":"master","last_synced_at":"2025-04-14T12:58:48.934Z","etag":null,"topics":["benchmark-framework","deep-learning","dgl","graph-deep-learning","graph-neural-networks","graph-representation-learning","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2003.00982","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/graphdeeplearning.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}},"created_at":"2020-03-03T03:42:50.000Z","updated_at":"2025-04-13T03:29:50.000Z","dependencies_parsed_at":"2022-07-16T10:46:08.805Z","dependency_job_id":"b31dfb77-f238-49e4-800a-18ec746577cf","html_url":"https://github.com/graphdeeplearning/benchmarking-gnns","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/graphdeeplearning%2Fbenchmarking-gnns","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphdeeplearning%2Fbenchmarking-gnns/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphdeeplearning%2Fbenchmarking-gnns/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/graphdeeplearning%2Fbenchmarking-gnns/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/graphdeeplearning","download_url":"https://codeload.github.com/graphdeeplearning/benchmarking-gnns/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254292042,"owners_count":22046426,"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":["benchmark-framework","deep-learning","dgl","graph-deep-learning","graph-neural-networks","graph-representation-learning","pytorch"],"created_at":"2024-07-31T02:00:38.800Z","updated_at":"2025-05-15T07:06:17.077Z","avatar_url":"https://github.com/graphdeeplearning.png","language":"Jupyter Notebook","readme":"\n\n# Benchmarking Graph Neural Networks\n\n\u003cbr\u003e\n\n## Updates\n\n**May 10, 2022**\n* Project based on DGL 0.6.1 and higher. See the relevant dependencies defined in the environment yml files ([CPU](./environment_cpu.yml), [GPU](./environment_gpu.yml)).  \n* Updated technical report of the framework on [ArXiv](https://arxiv.org/pdf/2003.00982.pdf).\n* Added [AQSOL dataset](https://www.nature.com/articles/s41597-019-0151-1), which is similar to ZINC for graph regression task, but has a real-world measured chemical target. \n* Added mathematical datasets -- GraphTheoryProp and CYCLES which are useful to test GNNs on specific theoretical graph properties.  \n* Fixed [issue #57](https://github.com/graphdeeplearning/benchmarking-gnns/issues/57).  \n\n**Oct 7, 2020**\n* Repo updated to DGL 0.5.2 and PyTorch 1.6.0. Please update your environment using yml files ([CPU](./environment_cpu.yml), [GPU](./environment_gpu.yml)).\n* Added [ZINC-full](./data/script_download_molecules.sh) dataset (249K molecular graphs) with [scripts](./scripts/ZINC-full/).\n\n\n**Jun 11, 2020**\n* Second release of the project. Major updates : \n\t+ Added experimental pipeline for Weisfeiler-Lehman-GNNs operating on dense rank-2 tensors.\n\t+ Added a leaderboard for all datasets.\n\t+ Updated PATTERN dataset.\n\t+ Fixed bug for PATTERN and CLUSTER accuracy.\n\t+ Moved first release to this [branch](https://github.com/graphdeeplearning/benchmarking-gnns/tree/arXivV1).\n* New ArXiv's version of the [paper](https://arxiv.org/pdf/2003.00982.pdf).\n\n\n**Mar 3, 2020**\n* First release of the project.\n\n\n\n\u003cbr\u003e\n\n\u003cimg src=\"./docs/gnns.jpg\" align=\"right\" width=\"350\"/\u003e\n\n\n## 1. Benchmark installation\n\n[Follow these instructions](./docs/01_benchmark_installation.md) to install the benchmark and setup the environment.\n\n\n\u003cbr\u003e\n\n## 2. Download datasets\n\n[Proceed as follows](./docs/02_download_datasets.md) to download the benchmark datasets.\n\n\n\u003cbr\u003e\n\n## 3. Reproducibility \n\n[Use this page](./docs/03_run_codes.md) to run the codes and reproduce the published results.\n\n\n\u003cbr\u003e\n\n## 4. Adding a new dataset \n\n[Instructions](./docs/04_add_dataset.md) to add a dataset to the benchmark.\n\n\n\u003cbr\u003e\n\n## 5. Adding a Message-passing GCN\n\n[Step-by-step directions](./docs/05_add_mpgcn.md) to add a MP-GCN to the benchmark.\n\n\n\u003cbr\u003e\n\n## 6. Adding a Weisfeiler-Lehman GNN\n\n[Step-by-step directions](./docs/06_add_wlgnn.md) to add a WL-GNN to the benchmark.\n\n\n\u003cbr\u003e\n\n## 7. Leaderboards\n\nFull leaderboards coming soon on [paperswithcode.com](https://paperswithcode.com/paper/benchmarking-graph-neural-networks).\n\n\n\u003cbr\u003e\n\n## 8. Reference \n\n[ArXiv's paper](https://arxiv.org/pdf/2003.00982.pdf)\n```\n@article{dwivedi2020benchmarkgnns,\n  title={Benchmarking Graph Neural Networks},\n  author={Dwivedi, Vijay Prakash and Joshi, Chaitanya K and Luu, Anh Tuan and Laurent, Thomas and Bengio, Yoshua and Bresson, Xavier},\n  journal={arXiv preprint arXiv:2003.00982},\n  year={2020}\n}\n```\n\n\n\n\u003cbr\u003e\u003cbr\u003e\u003cbr\u003e\n\n","funding_links":[],"categories":["Graph","Jupyter Notebook","其他_图神经网络GNN"],"sub_categories":["Graph Deep Learning","Others","网络服务_其他"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraphdeeplearning%2Fbenchmarking-gnns","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgraphdeeplearning%2Fbenchmarking-gnns","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraphdeeplearning%2Fbenchmarking-gnns/lists"}