BAFFLE: A Baseline of Backpropagation-Free Federated Learning

TL;DR

BAFFLE introduces a backpropagation-free federated learning method that replaces gradient computation with multiple forward passes, reducing resource use and enhancing security on edge devices.

Contribution

It proposes a novel federated learning approach that eliminates backpropagation, making training more efficient and secure for edge devices.

Findings

Achieves acceptable training results on deep models.

Compatible with hardware optimization and model pruning.

Reduces computational and storage overhead.

Abstract

Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation is replaced by multiple forward processes to estimate gradients. BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server. Empirically we use BAFFLE to train deep models from scratch or to finetune pretrained models, achieving acceptable results. Code is available in https://github.com/FengHZ/BAFFLE.