DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices

This repository is the official implementation of [DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices]. (Accepted by NeurIPS 2024)

Requirements

To install requirements:

pip install -r requirements.txt

We use wandb to keep a log of our experiments. If you don't have a wandb account, just install it and use it as offline mode.

pip install wandb
wandb off

Training & Evaluation

To train the model(s) in the paper, run this command:

python ./fedml_experiments/standalone/domain_generalization/main.py \
       --model dapperfl 
       --dataset fl_officecaltech 
       --backbone resnet18

Arguments

You can modify the arguments to run DapperFL on other settings. The arguments are described as follows:

Arguments	Description
prefix	A prefix for logging.
communication_epoch	Total communication rounds of Federated Learning.
local_epoch	Local epochs for local model updating.
parti_num	Number of participants.
model	Name of FL framework.
dataset	Datasets used in the experiment. Options: fl_officecaltech, fl_digits.
pr_strategy	Pruning ratio used to prune local models. Options: 0 (without pruning), 0.1 ~ 0.9, AD (adaptive pruning).
backbone	Backbone global model. Options: resnet10, resnet18.
alpha	Coefficient alpha in co-pruning. Default: 0.9.
alpha_min	Coefficient alpha_min in co-pruning. Default: 0.1.
epsilon	Coefficient epsilon in co-pruning. Default: 0.2.
reg_coeff	Coefficient for L2 regularization. Default: 0.01.
seed	Random seed.