Federated Learning on Stochastic Neural Networks

TL;DR

This paper introduces federated stochastic neural networks, a novel approach combining federated learning with stochastic neural models to better handle noisy, non-i.i.d. data on edge devices, enhancing privacy and robustness.

Contribution

It proposes integrating stochastic neural networks into federated learning to estimate true data states and quantify latent noise, improving model accuracy under data uncertainties.

Findings

Effective in handling non-i.i.d. data

Improves noise estimation and data robustness

Demonstrates superior performance in experiments

Abstract

Federated learning is a machine learning paradigm that leverages edge computing on client devices to optimize models while maintaining user privacy by ensuring that local data remains on the device. However, since all data is collected by clients, federated learning is susceptible to latent noise in local datasets. Factors such as limited measurement capabilities or human errors may introduce inaccuracies in client data. To address this challenge, we propose the use of a stochastic neural network as the local model within the federated learning framework. Stochastic neural networks not only facilitate the estimation of the true underlying states of the data but also enable the quantification of latent noise. We refer to our federated learning approach, which incorporates stochastic neural networks as local models, as Federated stochastic neural networks. We will present numerical experiments demonstrating the performance and effectiveness of our method, particularly in handling non-independent and identically distributed data.