Channel-driven Decentralized Bayesian Federated Learning for Trustworthy Decision Making in D2D Networks

TL;DR

This paper introduces a novel decentralized Bayesian federated learning approach for D2D networks that utilizes channel noise as a natural mechanism for MCMC sampling, enhancing trustworthy decision-making.

Contribution

It proposes leveraging channel noise in D2D links as a means for MCMC sampling in Bayesian FL, integrating communication imperfections into the learning process.

Findings

Channel noise can be effectively used for MCMC sampling in Bayesian FL.

The proposed method shows advantages over traditional FL in certain scenarios.

Limitations include potential challenges in noise control and convergence.

Abstract

Bayesian Federated Learning (FL) offers a principled framework to account for the uncertainty caused by limitations in the data available at the nodes implementing collaborative training. In Bayesian FL, nodes exchange information about local posterior distributions over the model parameters space. This paper focuses on Bayesian FL implemented in a device-to-device (D2D) network via Decentralized Stochastic Gradient Langevin Dynamics (DSGLD), a recently introduced gradient-based Markov Chain Monte Carlo (MCMC) method. Based on the observation that DSGLD applies random Gaussian perturbations of model parameters, we propose to leverage channel noise on the D2D links as a mechanism for MCMC sampling. The proposed approach is compared against a conventional implementation of frequentist FL based on compression and digital transmission, highlighting advantages and limitations.