Robust Federated Learning by Mixture of Experts

Abstract

We present a novel weighted average model based on the mixture of experts (MoE) concept to provide robustness in Federated learning (FL) against the poisoned/corrupted/outdated local models. These threats along with the non-IID nature of data sets can considerably diminish the accuracy of the FL model. Our proposed MoE-FL setup relies on the trust between users and the server where the users share a portion of their public data sets with the server. The server applies a robust aggregation method by solving the optimization problem or the Softmax method to highlight the outlier cases and to reduce their adverse effect on the FL process. Our experiments illustrate that MoE-FL outperforms the performance of the traditional aggregation approach for high rate of poisoned data from attackers.

References in corpus (7)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Robust Aggregation for Federated Learning
• How To Backdoor Federated Learning
• EMNIST: an extension of MNIST to handwritten letters
• Can You Really Backdoor Federated Learning?
• A generic framework for privacy preserving deep learning
• A Unified Theory of Decentralized SGD with Changing Topology and Local Updates