Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning

TL;DR

This paper introduces a privacy-preserving federated learning method called SCBF that uses channel-based updates and pruning to enhance model performance and convergence speed without sharing sensitive data.

Contribution

The paper proposes a novel channel-based update algorithm with pruning for federated learning, improving privacy, convergence speed, and model performance over existing methods.

Findings

SCBF achieves comparable performance to federated averaging.

Pruning accelerates model convergence.

Channel-based updates enhance privacy and efficiency.

Abstract

Artificial neural network has achieved unprecedented success in a wide variety of domains such as classifying, predicting and recognizing objects. This success depends on the availability of big data since the training process requires massive and representative data sets. However, data collection is often prevented by privacy concerns and people want to take control over their sensitive information during both training and using processes. To address this problem, we propose a privacy-preserving method for the distributed system, Stochastic Channel-Based Federated Learning (SCBF), which enables the participants to train a high-performance model cooperatively without sharing their inputs. We design, implement and evaluate a channel-based update algorithm for the central server in a distributed system, which selects the channels with regard to the most active features in a training loop and uploads them as learned information from local datasets. A pruning process is applied to the algorithm based on the validation set, which serves as a model accelerator. In the experiment, our model presents equal performances and higher saturating speed than the Federated Averaging method which reveals all the parameters of local models to the server when updating. We also demonstrate that the converging rates could be increased by introducing a pruning process.