PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929732891705344 |
|---|---|
| author | Zhang, Jianqing Liu, Yang Hua, Yang Wang, Hao Song, Tao Xue, Zhengui Ma, Ruhui Cao, Jian |
| author_facet | Zhang, Jianqing Liu, Yang Hua, Yang Wang, Hao Song, Tao Xue, Zhengui Ma, Ruhui Cao, Jian |
| contents | Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL)has gained significant prominence as a research direction within the FL domain. Whereas traditional FL (tFL) focuses on jointly learning a global model, pFL aims to balance each client's global and personalized goals in FL settings. To foster the pFL research community, we started and built PFLlib, a comprehensive pFL library with an integrated benchmark platform. In PFLlib, we implemented 37 state-of-the-art FL algorithms (8 tFL algorithms and 29 pFL algorithms) and provided various evaluation environments with three statistically heterogeneous scenarios and 24 datasets. At present, PFLlib has gained more than 1600 stars and 300 forks on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04992 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark Zhang, Jianqing Liu, Yang Hua, Yang Wang, Hao Song, Tao Xue, Zhengui Ma, Ruhui Cao, Jian Machine Learning Distributed, Parallel, and Cluster Computing Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL)has gained significant prominence as a research direction within the FL domain. Whereas traditional FL (tFL) focuses on jointly learning a global model, pFL aims to balance each client's global and personalized goals in FL settings. To foster the pFL research community, we started and built PFLlib, a comprehensive pFL library with an integrated benchmark platform. In PFLlib, we implemented 37 state-of-the-art FL algorithms (8 tFL algorithms and 29 pFL algorithms) and provided various evaluation environments with three statistically heterogeneous scenarios and 24 datasets. At present, PFLlib has gained more than 1600 stars and 300 forks on GitHub. |
| title | PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2312.04992 |