appfl

We have hosted the application appfl in order to run this application in our online workstations with Wine or directly.

Quick description about appfl:

APPFL (Advanced Privacy-Preserving Federated Learning) is a Python framework enabling researchers to easily build and benchmark privacy-aware federated learning solutions. It supports flexible algorithm development, differential privacy, secure communications, and runs efficiently on HPC and multi-GPU setups.

Features:

• Implements differential privacy and client authentication
• Modular plug-and-play aggregation, scheduling, trainers
• Supports synchronous and asynchronous FL algorithms
• Multi-GPU training via PyTorch DDP
• Integrates with MONAI for healthcare workflows
• Scalable on HPC using MPI/gRPC-based client-server setup

Programming Language: Python.
Categories: