FedAH: Aggregated Head for Personalized Federated Learning

This project FedAH is based on the open source project PFLlib development.

Environments

Install CUDA.

Install conda and activate conda.

conda env create -f env_cuda_latest.yaml # You may need to downgrade the torch using pip to match CUDA version

How to start simulating (examples for FedAH)

• Create proper environments (see Environments).

• Download this project to an appropriate location using git.

  git clone https://github.com/heyuepeng/FedAH.git
  

• Run evaluation:

  cd ./system
  python main.py -data MNIST -m cnn -algo FedAH -gr 2000 -did 0 # using the MNIST dataset, the FedAH algorithm, and the 4-layer CNN model
  

  Or you can uncomment the lines you need in ./system/examples.sh and run:

  cd ./system
  sh examples.sh
  

Note: The hyper-parameters have not been tuned for the algorithms. The values in ./system/examples.sh are just examples. You need to tune the hyper-parameters by yourself.