PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark
This provides a beginner-friendly resource for researchers in federated learning, though it is incremental as it builds on existing methods without introducing new algorithmic paradigms.
The authors tackled the need for accessible tools in personalized federated learning (pFL) by developing PFLlib, a library and benchmark platform that includes 37 state-of-the-art algorithms and evaluation across 24 datasets, resulting in over 1600 GitHub stars and 300 forks.
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.