TsingZ0/PFLlib
A personalized federated learning library and benchmark built on PyTorch for distributed ML training.
Not currently ranked — collecting fresh signals.
star history
PFLlib is a beginner-friendly federated learning library that enables model training across decentralized data sources without sharing raw data. It provides implementations of federated algorithms (FedAvg, FedCP, GPFL, FedDBE) along with benchmarks for evaluation. Users can create FL scenarios and run algorithms via provided scripts, supporting datasets like ImageNet and DomainNet with various heterogeneity configurations.
Frequently asked
- What is TsingZ0/PFLlib?
- A personalized federated learning library and benchmark built on PyTorch for distributed ML training.
- Is PFLlib open source?
- Yes — TsingZ0/PFLlib is open source, released under the Apache-2.0 license.
- What language is PFLlib written in?
- TsingZ0/PFLlib is primarily written in Python.
- How popular is PFLlib?
- TsingZ0/PFLlib has 2.1k stars on GitHub.
- Where can I find PFLlib?
- TsingZ0/PFLlib is on GitHub at https://github.com/TsingZ0/PFLlib.