{"id":24404031,"url":"https://github.com/jsmjie/fedbase","last_synced_at":"2025-12-14T19:07:40.515Z","repository":{"id":57130367,"uuid":"431779589","full_name":"jsmjie/FedBase","owner":"jsmjie","description":"An easy, modularized, DIY Federated Learning framework with many baselines for individual researchers.","archived":false,"fork":false,"pushed_at":"2023-05-24T13:30:27.000Z","size":60494,"stargazers_count":16,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-18T14:55:09.819Z","etag":null,"topics":["fl","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","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/jsmjie.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}},"created_at":"2021-11-25T09:07:17.000Z","updated_at":"2025-05-14T07:58:48.000Z","dependencies_parsed_at":"2023-07-28T21:13:42.800Z","dependency_job_id":null,"html_url":"https://github.com/jsmjie/FedBase","commit_stats":null,"previous_names":["jie-ma-ai/fedbase"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jsmjie/FedBase","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jsmjie%2FFedBase","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jsmjie%2FFedBase/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jsmjie%2FFedBase/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jsmjie%2FFedBase/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jsmjie","download_url":"https://codeload.github.com/jsmjie/FedBase/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jsmjie%2FFedBase/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002406,"owners_count":26083374,"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":"2025-10-09T02:00:07.460Z","response_time":59,"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":["fl","pytorch"],"created_at":"2025-01-20T03:45:44.515Z","updated_at":"2025-10-10T01:32:40.498Z","avatar_url":"https://github.com/jsmjie.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FedBase\nAn easy, modularized, DIY Federated Learning framework with many baselines for individual researchers.\n\n## Installation\n[fedbase @ pypi](https://pypi.org/project/fedbase/)\n```python\npip install --upgrade fedbase\n```\n\n## Baselines\n1. Centralized training\n2. Local training\n3. FedAvg, [Communication-Efficient Learning of Deep Networksfrom Decentralized Data](https://arxiv.org/abs/1602.05629)\n4. FedAvg + Finetune\n5. Fedprox, [Federated Optimization in Heterogeneous Networks](https://arxiv.org/abs/1812.06127)\n5. Ditto, [Ditto: Fair and Robust Federated Learning Through Personalization](https://arxiv.org/abs/2012.04221)\n6. WeCFL, [On the Convergence of Clustered Federated Learning](https://arxiv.org/abs/2202.06187)\n7. IFCA, [An Efficient Framework for Clustered Federated Learning](https://arxiv.org/abs/2006.04088)\n8. FeSEM, [Multi-Center Federated Learning](https://arxiv.org/abs/2005.01026)\n8. To be continued...\n\n## Three steps to achieve FedAvg!\n1. Data partition\n2. Nodes and server simulation\n3. Train and test\n\n## Design philosophy\n1. Dataset\n    1. Dataset\n        1. MNIST\n        2. CIFAR-10\n        3. Fashion-MNIST\n        4. ...\n    2. Dataset partition\n        1. IID\n        2. Non-IID\n            1. Dirichlet distribution\n            2. N-class\n            3. ...\n        3. Fake data\n        4. ...\n    \u003c!-- 3. Batch_size --\u003e\n2. Node\n    1. Local dataset\n    2. Model\n    3. Objective\n    4. Optimizer\n    5. Local update\n    6. Test\n3. Server\n    1. Model\n    2. Aggregate\n    3. Distribute\n4. Server \u0026 Node\n    1. Topology\n    2. Client sampling\n    3. Exchange message\n5. Baselines\n    1. Global\n    2. Local\n    3. FedAvg\n6. Visualization\n\n## How to develop your own FL with fedbase?","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjsmjie%2Ffedbase","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjsmjie%2Ffedbase","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjsmjie%2Ffedbase/lists"}