Shypd.aiThe largest open index of AI toolsPFLlib is an Open Source & Models tool that provides a beginner-friendly library and benchmark for federated learning. It allows users to master federated learning in hours and run experiments on a PC.
Trending
About
PFLlib is a comprehensive and beginner-friendly library and benchmark for personalized federated learning (PFL). It enables users to quickly grasp and implement federated learning concepts, even on a personal computer. The platform supports 39 traditional and personalized FL algorithms, 3 scenarios, and 24 datasets, facilitating extensive research and experimentation. Key features include real-machine deployment capabilities with HtFL-OnDevice, privacy evaluation, and systematic research support. PFLlib primarily focuses on data (statistical) heterogeneity, offering tools to generate various non-IID data distributions. It also provides an easy-to-extend framework for adding new data or algorithms, fostering community contributions.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
