{"id":30294471,"url":"https://github.com/linkedin/pass-gnn","last_synced_at":"2025-08-17T01:35:10.915Z","repository":{"id":45622999,"uuid":"438893824","full_name":"linkedin/PASS-GNN","owner":"linkedin","description":null,"archived":false,"fork":false,"pushed_at":"2021-12-17T01:54:36.000Z","size":136,"stargazers_count":35,"open_issues_count":0,"forks_count":10,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-04-13T23:22:26.570Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/linkedin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-12-16T07:11:02.000Z","updated_at":"2024-01-04T17:04:14.000Z","dependencies_parsed_at":"2022-09-12T00:31:55.677Z","dependency_job_id":null,"html_url":"https://github.com/linkedin/PASS-GNN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/linkedin/PASS-GNN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linkedin%2FPASS-GNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linkedin%2FPASS-GNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linkedin%2FPASS-GNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linkedin%2FPASS-GNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/linkedin","download_url":"https://codeload.github.com/linkedin/PASS-GNN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/linkedin%2FPASS-GNN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270796216,"owners_count":24647319,"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","status":"online","status_checked_at":"2025-08-16T02:00:11.002Z","response_time":91,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":"2025-08-17T01:35:08.436Z","updated_at":"2025-08-17T01:35:10.901Z","avatar_url":"https://github.com/linkedin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PASS: Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks\n\nPASS is a neighborhood sampler for graph neural network models.\nPASS samples neighbors informative for a target task by optimizing a sampling policy directly towards task performance.\n\nYou can see our KDD 2021 paper [\"Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks\"](https://minjiyoon.xyz/Paper/PASS.pdf) for more details.\nThis implementation is based on Pytorch.\n\n## Requirement\n\nUse the package manager pip to install requirements:\n\n```bash\npip install -r requirements.txt\n```\n\n## Dataset\n\nWe use open-source dataset, [GNN-benchmark](https://github.com/shchur/gnn-benchmark), for our experiments.\nOur code reads npz-format graph datasets.\n\n\n## Usage\n\nIn **args.py**, you can find a list of hyperparameters.\nSome of them are related to Neural Network training, some are related to GNN structure, and the others are related to our sampling strategies.\nYou can find descriptions of hyperparameters in **args.py** file.\n\nHere is the example command to run PASS.\n```bash\npython test.py --dataset cora --sample_num 5\n```\nOnce you download all npz-format datasets in **run.sh** into ./Data/ directory, you can simply run **run.sh** to test all datasets with different sampling numbers.\n\n\n## Citation\n\nPlease consider citing the following paper when using our code for your application.\n```bash\n@inproceedings{yoon2021performance,\n  title={Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks},\n  author={Yoon, Minji and Gervet, Th{\\'e}ophile and Shi, Baoxu and Niu, Sufeng and He, Qi and Yang, Jaewon},\n  booktitle={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \\\u0026 Data Mining},\n  pages={2046--2056},\n  year={2021}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flinkedin%2Fpass-gnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flinkedin%2Fpass-gnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flinkedin%2Fpass-gnn/lists"}