Federated Learning on Stochastic Neural Networks
This addresses data quality issues in federated learning for privacy-preserving applications, but it is incremental as it adapts an existing neural network type to a known bottleneck.
The paper tackles the problem of latent noise in client data within federated learning by proposing stochastic neural networks as local models to estimate true data states and quantify noise, showing effectiveness in handling non-IID data through numerical experiments.
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.