Federated Learning via Plurality Vote
In this paper, we propose a new scheme named federated learning via plurality vote (FedVote). In each communication round of FedVote, clients transmit binary or ternary weights to the server with low communication overhead. The model parameters are aggregated via weighted voting to enhance the resilience against Byzantine attacks. When deployed for inference, the model with binary or ternary weights is resource-friendly to edge devices. Our results demonstrate that the proposed method can reduce quantization error and converges faster compared to the methods directly quantizing the model updates.
Prerequisites
pip3 install -r requirements.txtThe datasets have been preprocessed under data directory.
Example
Run the example with fashion mnist dataset:
python3 train_fmnist.pyThe script will load the configuration file config_fmnist.yaml and data matrices under data/fmnist/.
You can change the dataset, for example, to CIFAR-10, by modifying the config.yaml to
test_data_dir: data/cifar/test.dat
train_data_dir: data/cifar/train.dat
sample_size:
- 32
- 32
channels: 3
classes: 10