{"id":13473396,"url":"https://github.com/squareRoot3/Rethinking-Anomaly-Detection","last_synced_at":"2025-03-26T19:34:05.745Z","repository":{"id":38793517,"uuid":"498571454","full_name":"squareRoot3/Rethinking-Anomaly-Detection","owner":"squareRoot3","description":"\"Rethinking Graph Neural Networks for Anomaly Detection\" in ICML 2022","archived":false,"fork":false,"pushed_at":"2024-06-25T09:30:38.000Z","size":18,"stargazers_count":175,"open_issues_count":0,"forks_count":29,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-10-30T06:31:54.688Z","etag":null,"topics":["anomaly-detection","deep-learning","graph-neural-networks"],"latest_commit_sha":null,"homepage":"https://proceedings.mlr.press/v162/tang22b.html","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/squareRoot3.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-06-01T02:58:21.000Z","updated_at":"2024-10-26T21:06:03.000Z","dependencies_parsed_at":"2024-06-25T10:55:21.860Z","dependency_job_id":null,"html_url":"https://github.com/squareRoot3/Rethinking-Anomaly-Detection","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/squareRoot3%2FRethinking-Anomaly-Detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/squareRoot3%2FRethinking-Anomaly-Detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/squareRoot3%2FRethinking-Anomaly-Detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/squareRoot3%2FRethinking-Anomaly-Detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/squareRoot3","download_url":"https://codeload.github.com/squareRoot3/Rethinking-Anomaly-Detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245722826,"owners_count":20661831,"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":["anomaly-detection","deep-learning","graph-neural-networks"],"created_at":"2024-07-31T16:01:03.278Z","updated_at":"2025-03-26T19:34:05.411Z","avatar_url":"https://github.com/squareRoot3.png","language":"Python","funding_links":[],"categories":["Python","异常检测"],"sub_categories":[],"readme":"# Rethinking Graph Neural Networks for Anomaly Detection \n\nThis is the official implementation for the following paper:\n\n[Rethinking Graph Neural Networks for Anomaly Detection](https://proceedings.mlr.press/v162/tang22b.html)  \n*Jianheng Tang, Jiajin Li, Ziqi Gao, Jia Li*  \nICML 2022\n\nBWGNN has been integrated into [GADBench](https://github.com/squareRoot3/GADBench), a comprehensive benchmark for (semi-)supervised graph anomaly detection.\n\n\nDependencies\n----------------------\n- pytorch 1.9.0\n- dgl 0.8.1\n- sympy\n- argparse\n- sklearn\n\n\nHow to run\n--------------------------------\nThe T-Finance and T-Social datasets developed in the paper are on [google drive](https://drive.google.com/drive/folders/1PpNwvZx_YRSCDiHaBUmRIS3x1rZR7fMr?usp=sharing). Download and unzip all files in the `dataset` folder.\n\n`plot.zip` in the above link is used to reproduce Figure 1 and 2 in our paper. You can unzip it and directly run the corresponding `.py` files.\n\nThe Yelp and Amazon datasets will be automatically downloaded from the Internet. \n\nTrain BWGNN (homo) on Amazon (40%): \n```\npython main.py --dataset amazon --train_ratio 0.4 --hid_dim 64 \\\n--order 2 --homo 1 --epoch 100 --run 1\n```\n`amazon` can be replaced by other datasets: `yelp/tfinance/tsocial`\n\nTrain BWGNN (hetero) on Yelp (1%):\n```\npython main.py --dataset yelp --train_ratio 0.01 --hid_dim 64 \\\n--order 2 --homo 0 --epoch 100 --run 1\n```\nBWGNN (hetero) only supports Yelp and Amazon.\n\nTrain BWGNN (homo) on T-Social (40%):\n```\npython main.py --dataset tsocial --train_ratio 0.4 --hid_dim 10 \\\n--order 5 --homo 1 --epoch 100 --run 1\n```\n\n\n\nIf you use this package and find it useful, please cite our ICML paper using the following BibTeX. Thanks! :)\n\n```\n@InProceedings{tang2022rethinking,\n  title = \t {Rethinking Graph Neural Networks for Anomaly Detection},\n  author =       {Tang, Jianheng and Li, Jiajin and Gao, Ziqi and Li, Jia},\n  booktitle = \t {International Conference on Machine Learning},\n  year = \t {2022},\n}\n```\nYou can find a more detailed BibTex or other citation formats [here](https://proceedings.mlr.press/v162/tang22b.html).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FsquareRoot3%2FRethinking-Anomaly-Detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FsquareRoot3%2FRethinking-Anomaly-Detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FsquareRoot3%2FRethinking-Anomaly-Detection/lists"}