{"id":13779615,"url":"https://github.com/datake/AdaGCN","last_synced_at":"2025-05-11T13:31:01.894Z","repository":{"id":201989252,"uuid":"332146234","full_name":"datake/AdaGCN","owner":"datake","description":"Official Implementation of AdaGCN (ICLR 2021)","archived":false,"fork":false,"pushed_at":"2022-01-03T17:06:54.000Z","size":8613,"stargazers_count":59,"open_issues_count":2,"forks_count":12,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-08-03T18:14:13.101Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/datake.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}},"created_at":"2021-01-23T06:45:07.000Z","updated_at":"2024-04-24T06:22:24.000Z","dependencies_parsed_at":null,"dependency_job_id":"647151ce-7d20-4f68-80df-1d717135e046","html_url":"https://github.com/datake/AdaGCN","commit_stats":null,"previous_names":["datake/adagcn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datake%2FAdaGCN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datake%2FAdaGCN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datake%2FAdaGCN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/datake%2FAdaGCN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/datake","download_url":"https://codeload.github.com/datake/AdaGCN/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225056721,"owners_count":17414191,"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":"2024-08-03T18:01:07.135Z","updated_at":"2024-11-17T15:30:36.637Z","avatar_url":"https://github.com/datake.png","language":"Python","funding_links":[],"categories":["2021"],"sub_categories":[],"readme":"# Official Pytorch Implementation of \"AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models\" (ICLR 2021)\n\nPlease refer to [openreview](https://openreview.net/forum?id=QkRbdiiEjM) (ICLR 2021) to look into the details of our paper.\n\n![Alt text](https://github.com/datake/AdaGCN/raw/main/AdaGCN.png)\n\n\n## Enviromment\n\n```\npython3.6  \ncuda11.0  \ntorch1.7.1\n```\n\n## Run the code （Datasets: citeseer, cora_ml, pubmed and ms_academic）\n\n\n\n#### Baseline: GCN\n\n```\npython main.py --trainsize 20 --dataset citeseer --niter 5 --nseed 20 --model GCN --dropout 0.5 --reg 5e-4\n```\n\n#### Baseline: APPNP or PPNP\n\n```\npython main.py --trainsize 20 --dataset citeseer --niter 5 --nseed 20 --model APPNP --dropout 0.5 --early 1 --patience 300 --max 500 --reg 5e-3\n```\n\n#### AdaGCN on Four datasets:\n\n```\npython main.py --trainsize 20 --dataset citeseer --niter 5 --nseed 20 --model AdaGCN --layers 15 --hid_AdaGCN 5000 --dropout 0.0 --weight_decay 1e-3 --early 1 --patience 300 --max 500 --reg 5e-3   \npython main.py --trainsize 20 --dataset cora_ml --niter 5 --nseed 20 --model AdaGCN --layers 12 --hid_AdaGCN 5000 --dropout 0.0 --weight_decay 1e-4 --early 1 --patience 300 --max 500 --reg 5e-3   \npython main.py --trainsize 20 --dataset pubmed --niter 5 --nseed 20 --model AdaGCN --layers 20 --hid_AdaGCN 5000 --dropout 0.2 --weight_decay 1e-4 --early 1 --patience 300 --max 500 --reg 5e-3   \npython main.py --trainsize 20 --dataset ms_academic --niter 5 --nseed 20 --model AdaGCN --layers 5 --hid_AdaGCN 3000 --dropout 0.2 --weight_decay 1e-4 --early 1 --patience 300 --max 500 --reg 5e-3\n```\n\n**Results:** \n\n| Dataset  | Average Accuracy | Std |\n| ------------- | ------------- | ------------- |\n| Citeseer  | 76.68  | 0.20  |\n| Cora-ML  | 85.97  | 0.20  |\n| PubMed  | 79.95  | 0.21  |\n| MS Academic  | 93.17  | 0.07  |\n\n## Acknowledgement\n\nOur code is directly adapted from PPNP paper **Predict then Propagate: Graph Neural Networks meet Personalized PageRank** (ICLR 2019) github: https://github.com/klicperajo/ppnp.\n\n## Contact\n\nPlease refer to ajksunke@pku.edu.cn in case you have any questions. \n\n## Cite\nPlease cite our paper if you use the model or this code in your own work:\n```\n@inproceedings{sun2020adagcn,\n  title={AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models},\n  author={Sun, Ke and Zhu, Zhanxing and Lin, Zhouchen},\n  booktitle={International Conference on Learning Representations},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatake%2FAdaGCN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatake%2FAdaGCN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatake%2FAdaGCN/lists"}