{"id":22195349,"url":"https://github.com/amanpriyanshu/the-unlearning-protocol","last_synced_at":"2026-01-06T11:10:01.663Z","repository":{"id":264752755,"uuid":"893794315","full_name":"AmanPriyanshu/The-Unlearning-Protocol","owner":"AmanPriyanshu","description":"Choose which data to make your model forget (Unlearn!), but watch out - every deletion ripples!","archived":false,"fork":false,"pushed_at":"2024-11-26T05:40:53.000Z","size":4637,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-19T06:15:56.002Z","etag":null,"topics":["ai","artificial-intelligence","artificial-neural-networks","catastrophic-forgetting","deep-learning","deep-neural-networks","deeplearning","fairness","fairness-ai","fairness-ml","gradient-ascent","machine-learning","neural-network","neural-networks","privacy","privacy-enhancing-technologies","privacy-protection","privacy-tools","unlearn","unlearning"],"latest_commit_sha":null,"homepage":"https://amanpriyanshu.github.io/The-Unlearning-Protocol/","language":"HTML","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/AmanPriyanshu.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-25T08:17:31.000Z","updated_at":"2024-11-26T05:40:56.000Z","dependencies_parsed_at":"2024-11-26T06:38:42.073Z","dependency_job_id":null,"html_url":"https://github.com/AmanPriyanshu/The-Unlearning-Protocol","commit_stats":null,"previous_names":["amanpriyanshu/the-unlearning-protocol"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FThe-Unlearning-Protocol","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FThe-Unlearning-Protocol/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FThe-Unlearning-Protocol/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmanPriyanshu%2FThe-Unlearning-Protocol/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AmanPriyanshu","download_url":"https://codeload.github.com/AmanPriyanshu/The-Unlearning-Protocol/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245355979,"owners_count":20601835,"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":["ai","artificial-intelligence","artificial-neural-networks","catastrophic-forgetting","deep-learning","deep-neural-networks","deeplearning","fairness","fairness-ai","fairness-ml","gradient-ascent","machine-learning","neural-network","neural-networks","privacy","privacy-enhancing-technologies","privacy-protection","privacy-tools","unlearn","unlearning"],"created_at":"2024-12-02T13:18:18.125Z","updated_at":"2026-01-06T11:09:56.623Z","avatar_url":"https://github.com/AmanPriyanshu.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 The Unlearning Protocol Game\n![demo-unlearning](/assets/unlearn_demo.gif)\n\nAn interactive game that demonstrates machine unlearning through a neural network trained on demographic data. Experience firsthand how making models forget affects their behavior across different population groups!\n\n## 🎯 Educational Goals\nThis game helps players understand:\n- The concept and challenges of machine unlearning\n- How selective forgetting impacts model fairness\n- Ripple effects across demographic groups\n- The delicate balance between forgetting and maintaining performance\n\n## 🎮 How It Works\n\n### 1. The Forgetting Process\n- Select individual data points for the model to forget\n- Configure unlearning parameters (learning rate and epochs)\n- Watch how forgetting ripples through the model's behavior\n- Monitor performance changes across different demographics\n\n### 2. Impact Visualization\n- **Real-time Performance Tracking**: See how unlearning affects model accuracy\n- **Demographic Impact**: Monitor changes across age, education, and work hours\n- **Comparative Analysis**: Compare unlearning vs retraining results\n- **Global Statistics**: Track overall model health\n\n### 3. Strategic Elements\n- Choose which samples to forget wisely - not all forgetting is equal!\n- Balance aggressive vs gentle unlearning through parameter tuning\n- Monitor unintended consequences across different population groups\n- Aim for minimal collateral damage while achieving targeted forgetting\n\n## 🎲 How to Play\n\n1. **Sample Selection**\n   - Review candidate samples for unlearning\n   - Each sample shows key demographic information\n   - Consider potential ripple effects before choosing\n\n2. **Configure Unlearning**\n   - Adjust the learning rate (0.001 to 0.1)\n   - Set the number of unlearning epochs (1 to 50)\n   - Higher values = more aggressive forgetting\n\n3. **Monitor Impact**\n   - Watch performance changes across groups\n   - Compare with reference retraining results\n   - Look for unexpected demographic impacts\n\n## 🎯 Challenge Goals\n1. Successfully make the model forget targeted samples\n2. Maintain balanced performance across demographics\n3. Minimize accuracy drop on unrelated groups\n4. Find optimal unlearning parameters for different scenarios\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famanpriyanshu%2Fthe-unlearning-protocol","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famanpriyanshu%2Fthe-unlearning-protocol","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famanpriyanshu%2Fthe-unlearning-protocol/lists"}