{"id":13481087,"url":"https://github.com/KangchengHou/gntk","last_synced_at":"2025-03-27T11:31:47.983Z","repository":{"id":73468268,"uuid":"207126747","full_name":"KangchengHou/gntk","owner":"KangchengHou","description":"Implementation of Graph Neural Tangent Kernel (NeurIPS 2019)","archived":false,"fork":false,"pushed_at":"2020-01-28T00:56:42.000Z","size":5070,"stargazers_count":101,"open_issues_count":1,"forks_count":20,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-10-30T14:43:26.026Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KangchengHou.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":"2019-09-08T14:44:23.000Z","updated_at":"2024-10-14T14:46:01.000Z","dependencies_parsed_at":"2024-01-21T10:52:33.642Z","dependency_job_id":null,"html_url":"https://github.com/KangchengHou/gntk","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/KangchengHou%2Fgntk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KangchengHou%2Fgntk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KangchengHou%2Fgntk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KangchengHou%2Fgntk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KangchengHou","download_url":"https://codeload.github.com/KangchengHou/gntk/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245836223,"owners_count":20680335,"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":"2024-07-31T17:00:48.577Z","updated_at":"2025-03-27T11:31:47.390Z","avatar_url":"https://github.com/KangchengHou.png","language":"Python","funding_links":[],"categories":["Deep Learning"],"sub_categories":[],"readme":"# Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels\n\nThis repository implements Graph Neural Tangent Kernel (infinitely wide multi-layer GNNs trained by gradient descent), described in the following paper:\n\nSimon S. Du, Kangcheng Hou, Barnabás Póczos, Ruslan Salakhutdinov, Ruosong Wang, Keyulu Xu. Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels. NeurIPS 2019. [[arXiv]](https://arxiv.org/abs/1905.13192) [[Paper]](https://papers.nips.cc/paper/8809-graph-neural-tangent-kernel-fusing-graph-neural-networks-with-graph-kernels)\n\n\n## Test run\nUnzip the dataset file\n```\nunzip dataset.zip\n```\n\nHere we demonstrate how to use GNTK to perform classification on IMDB-BINARY dataset. We set the number of BLOCK operations to be 2, the number of MLP layers to be 2 and c_u to be 1.\n\nCompute the GNTK gram matrix\n```\nmkdir out\npython gram.py --dataset IMDBBINARY --num_mlp_layers 2 --num_layers 2 --scale uniform --jk 1 --out_dir out\n```\n\nClassification with kernel regression \n```\npython search.py --data_dir ./out --dataset IMDBBINARY\n```\n\nTherefore we get the hyper-parameter search results at `./out/grid_search.csv`.\n\n## Experiment for all datasets\nTo run the experiment described in our paper, please run `bash run_gram.sh` and `bash run_search.sh`\nin order.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKangchengHou%2Fgntk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FKangchengHou%2Fgntk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKangchengHou%2Fgntk/lists"}