Bayesian Federated Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing

Federated learning (FL) is a machine learning paradigm where the clients possess decentralized training data and the central server handles aggregation and scheduling. Typically, FL algorithms involve clients training their local models using stochastic gradient descent (SGD), which carries drawbacks such as slow convergence and being prone to getting stuck in suboptimal solutions. In this work, we propose a message passing based Bayesian federated learning (BFL) framework to avoid these drawbacks.Specifically, we formulate the problem of deep neural network (DNN) …

aggregation algorithms bayesian convergence cs.ai cs.lg data decentralized federated learning gradient machine machine learning paradigm scheduling server stochastic training training data turbo via