{"id":18950139,"url":"https://github.com/salesforce/gaea","last_synced_at":"2025-10-30T17:49:44.463Z","repository":{"id":39761490,"uuid":"317974959","full_name":"salesforce/GAEA","owner":"salesforce","description":"Data and code for Salesforce Research paper, GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning - https://arxiv.org/abs/2012.03900 . The paper provides methods for constraint graph augmentation and optimal facility placement problems","archived":false,"fork":false,"pushed_at":"2023-07-06T22:25:21.000Z","size":9046,"stargazers_count":9,"open_issues_count":3,"forks_count":2,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-06-01T23:26:18.352Z","etag":null,"topics":["ai","constraint-optimization","deep-reinforcement-learning","equity","fairness-ai","graph-algorithms","graph-machine-learning","graph-ml","ml","reinforcement-learning","resource-management","rl","social-network","social-network-analysis"],"latest_commit_sha":null,"homepage":"","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/salesforce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null}},"created_at":"2020-12-02T19:53:47.000Z","updated_at":"2023-08-13T03:50:50.000Z","dependencies_parsed_at":"2022-09-07T07:11:33.649Z","dependency_job_id":"4aed5726-353f-4ac9-9919-44294c9e13ec","html_url":"https://github.com/salesforce/GAEA","commit_stats":{"total_commits":14,"total_committers":4,"mean_commits":3.5,"dds":0.2857142857142857,"last_synced_commit":"f78509366e67480406e2253e2873bf4fc6babf56"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/salesforce/GAEA","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FGAEA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FGAEA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FGAEA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FGAEA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/salesforce","download_url":"https://codeload.github.com/salesforce/GAEA/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salesforce%2FGAEA/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281853658,"owners_count":26573095,"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":"2025-10-30T02:00:06.501Z","response_time":61,"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":["ai","constraint-optimization","deep-reinforcement-learning","equity","fairness-ai","graph-algorithms","graph-machine-learning","graph-ml","ml","reinforcement-learning","resource-management","rl","social-network","social-network-analysis"],"created_at":"2024-11-08T13:21:12.042Z","updated_at":"2025-10-30T17:49:44.430Z","avatar_url":"https://github.com/salesforce.png","language":"HTML","readme":"# GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning\n\nThis repository contains the data and code for [Salesforce Research](https://einstein.ai) paper: [GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning\n](https://arxiv.org/abs/2012.03900)\n\n## Citation\nIf you use this code, data or our results in your research, please cite as appropriate:\n\n```\n@inproceedings{ramachandran2021gaea,\n  title={GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning},\n  author={Ramachandran, Govardana Sachithanandam and Brugere, Ivan and Varshney, Lav R and Xiong, Caiming},\n  booktitle={Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society},\n  pages={884--894},\n  year={2021}\n}\n```\n\n## Prerequisites\n\n### Software\nInstall dependencies by running\n```\npip install -r requirements.txt\n```\nThe code was tested on \n```\ncuda 11.2\ntensorflow-gpu==2.6.0\nkeras==2.6.0\n```\n\n### Hardware\nWe ran on a Quadro GV100 with 32GB RAM. \n\n### Dataset \n1. Dataset merging public census, school, and transportation datasets for the city of Chicago is provided under data/{demographics | network | schools}\n2. For Facebook100 dataset download the data as described in http://sociograph.blogspot.com/2011/03/facebook100-data-and-parser-for-it.html and place the unziped data under data/facebook100\n\n\n## Experiments\n\nEdit repository path and the output path for the project in paths_inc.py .\n\nThe run_experiments.py generates all results for: \n\n1. Original graph \n2. Baseline method\n3. Proposed method\n\nOn each of the outputted graphs, we run monte carlo weighted walk simulations and estimate the distribution of expected rewards of walkers. On this distribution, we evaluate our main two criteria:\n\n1. Expected Utility\n2. Gini Index of Expected Utility\n\n### Graph editing on Chicago school network\n```python run_experiments.py --exp edit --graph chicago```\n\n### Graph editing on Facebook100 schools\n```python run_experiments.py --exp edit --graph fb --school Caltech36```\n\nOther school network we tried are: Mich67 and Reed98 \n\n### Graph editing on synthetic network\n```python run_experiments.py --exp edit --graph synthetic```\n\n### Facility Placement\n```python run_experiments.py --exp facility_placement --graph chicago```\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalesforce%2Fgaea","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsalesforce%2Fgaea","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalesforce%2Fgaea/lists"}