{"id":22878737,"url":"https://github.com/rkhosrowshahi/mormu","last_synced_at":"2026-01-30T05:11:31.835Z","repository":{"id":265777398,"uuid":"896622845","full_name":"rkhosrowshahi/MORMU","owner":"rkhosrowshahi","description":"A novel multi-objective responsible machine unlearning using NSGA-II","archived":false,"fork":false,"pushed_at":"2024-12-02T00:34:12.000Z","size":48097,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-31T14:32:40.152Z","etag":null,"topics":["evolutionary-algorithms","machine-unlearning","responsible-ai"],"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/rkhosrowshahi.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":"2024-11-30T21:21:26.000Z","updated_at":"2024-12-02T00:34:16.000Z","dependencies_parsed_at":"2024-11-30T22:35:59.088Z","dependency_job_id":"bdabbfd7-d849-4c9e-bfed-4f2aa87fca0e","html_url":"https://github.com/rkhosrowshahi/MORMU","commit_stats":null,"previous_names":["rkhosrowshahi/mormu"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rkhosrowshahi%2FMORMU","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rkhosrowshahi%2FMORMU/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rkhosrowshahi%2FMORMU/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rkhosrowshahi%2FMORMU/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rkhosrowshahi","download_url":"https://codeload.github.com/rkhosrowshahi/MORMU/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252961821,"owners_count":21832194,"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":["evolutionary-algorithms","machine-unlearning","responsible-ai"],"created_at":"2024-12-13T16:31:00.310Z","updated_at":"2026-01-30T05:11:31.766Z","avatar_url":"https://github.com/rkhosrowshahi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multi-Objective Responsible Machine Unlearning\n\nIn this project, we aim to propose a novel machine unlearning method for black-box neural networks such as Multi-layer Perceptron (MLP) and ConvNets (LeNet-5) using evolutionary multi-objective algorithm. We used non-dominated sorting genetic algorithm II (NSGA-II) []which is a meta-heuristic gradient-free algorithm to effectively optimize $`M \\ge 2`$ objectives with respect to parameters such as weights and biases in neural networks.\n\nThe datasets used:\n\n* Fashion-MNIST\n\nThere are two dataset splits in Fashion known as:\n\n1. Training data $`D_{train}`$\n2. Test data $`D_{test}`$\n\nFor the sake of unlearning, the training data is divided into two subsets as follows:\n\n1. Forget data $`D_{u}`$\n2. Retaining data $`D_{r}`$\n\nThe forgetting data is randomly selected from training data and the size is 1,000.\n\nThere are two networks to use and suggested commands are as follows:\n\n1. MLP (64 hidden units), 50K params\n\n    ```\n    python3 main.py --net mlp --dataset fashion --obj entropy_f1score --output_dir ./out/mlp-64 --steps 1000\n    ```\n\n2. LeNet-5, 60K params\n\n    ```\n    python3 main.py --net lenet --dataset fashion --obj entropy_f1score --output_dir ./out/lenet --steps 1000\n    ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frkhosrowshahi%2Fmormu","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frkhosrowshahi%2Fmormu","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frkhosrowshahi%2Fmormu/lists"}