{"id":13481152,"url":"https://github.com/weihua916/powerful-gnns","last_synced_at":"2025-05-16T14:05:42.741Z","repository":{"id":45251654,"uuid":"163207514","full_name":"weihua916/powerful-gnns","owner":"weihua916","description":"How Powerful are Graph Neural Networks?","archived":false,"fork":false,"pushed_at":"2021-07-01T16:45:36.000Z","size":32539,"stargazers_count":1216,"open_issues_count":19,"forks_count":224,"subscribers_count":25,"default_branch":"master","last_synced_at":"2025-04-19T15:56:22.380Z","etag":null,"topics":["deep-learning","graph-convolutional-neural-networks","graph-neural-networks"],"latest_commit_sha":null,"homepage":null,"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/weihua916.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":"2018-12-26T18:37:44.000Z","updated_at":"2025-04-17T21:37:16.000Z","dependencies_parsed_at":"2022-07-13T12:50:25.819Z","dependency_job_id":null,"html_url":"https://github.com/weihua916/powerful-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/weihua916%2Fpowerful-gnns","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weihua916%2Fpowerful-gnns/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weihua916%2Fpowerful-gnns/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/weihua916%2Fpowerful-gnns/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/weihua916","download_url":"https://codeload.github.com/weihua916/powerful-gnns/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254544146,"owners_count":22088807,"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":["deep-learning","graph-convolutional-neural-networks","graph-neural-networks"],"created_at":"2024-07-31T17:00:49.198Z","updated_at":"2025-05-16T14:05:37.731Z","avatar_url":"https://github.com/weihua916.png","language":"Python","funding_links":[],"categories":["Deep Learning","Python"],"sub_categories":[],"readme":"# How Powerful are Graph Neural Networks?\n\nThis repository is the official PyTorch implementation of the experiments in the following paper: \n\nKeyulu Xu*, Weihua Hu*, Jure Leskovec, Stefanie Jegelka. How Powerful are Graph Neural Networks? ICLR 2019. \n\n[arXiv](https://arxiv.org/abs/1810.00826) [OpenReview](https://openreview.net/forum?id=ryGs6iA5Km) \n\nIf you make use of the code/experiment or GIN algorithm in your work, please cite our paper (Bibtex below).\n```\n@inproceedings{\nxu2018how,\ntitle={How Powerful are Graph Neural Networks?},\nauthor={Keyulu Xu and Weihua Hu and Jure Leskovec and Stefanie Jegelka},\nbooktitle={International Conference on Learning Representations},\nyear={2019},\nurl={https://openreview.net/forum?id=ryGs6iA5Km},\n}\n```\n\n## Installation\nInstall PyTorch following the instuctions on the [official website] (https://pytorch.org/). The code has been tested over PyTorch 0.4.1 and 1.0.0 versions.\n\nThen install the other dependencies.\n```\npip install -r requirements.txt\n```\n\n## Test run\nUnzip the dataset file\n```\nunzip dataset.zip\n```\n\nand run\n\n```\npython main.py\n```\n\nThe default parameters are not the best performing-hyper-parameters used to reproduce our results in the paper. Hyper-parameters need to be specified through the commandline arguments. Please refer to our paper for the details of how we set the hyper-parameters. For instance, for the COLLAB and IMDB datasets, you need to add `--degree_as_tag` so that the node degrees are used for input node features.\n\nTo learn hyper-parameters to be specified, please type\n```\npython main.py --help\n```\n\n\n\n## Cross-validation strategy in the paper\nThe cross-validation in our paper only uses training and validation sets (no test set) due to small dataset size. Specifically, after obtaining 10 validation curves corresponding to 10 folds, we first took average of validation curves across the 10 folds (thus, we obtain an averaged validation curve), and then selected a single epoch that achieved the maximum averaged validation accuracy. Finally, the standard devision over the 10 folds was computed at the selected epoch. \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweihua916%2Fpowerful-gnns","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fweihua916%2Fpowerful-gnns","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fweihua916%2Fpowerful-gnns/lists"}