A beginner-friendly and comprehensive personalized federated learning library and benchmark platform.
37 traditional FL (tFL) or personalized FL (pFL) algorithms, 3 scenarios, and 24 datasets.
Enable collaborative AI model training across multiple devices or organizations while ensuring data privacy.
Designed to efficiently handle large-scale federated learning tasks with minimal GPU consumption.
Simple file structure, encapsulated function interface, with each FL algorithm requiring just two files.