A Learning-Based Incentive Mechanism for Federated Learning

TLDR

IoT devices generate vast data that cannot be centrally transmitted due to bandwidth, storage, and privacy limits, so federated learning aggregates locally trained models, yet incentive mechanisms for motivating edge participation remain largely unexplored. This work investigates an incentive mechanism to encourage edge nodes to contribute to federated learning model training. A deep reinforcement learning framework is proposed to compute optimal pricing for the parameter server and optimal training strategies for edge nodes, and its effectiveness is demonstrated through numerical experiments.

Abstract

Internet of Things (IoT) generates large amounts of data at the network edge. Machine learning models are often built on these data, to enable the detection, classification, and prediction of the future events. Due to network bandwidth, storage, and especially privacy concerns, it is often impossible to send all the IoT data to the data center for centralized model training. To address these issues, federated learning has been proposed to let nodes use the local data to train models, which are then aggregated to synthesize a global model. Most of the existing work has focused on designing learning algorithms with provable convergence time, but other issues, such as incentive mechanism, are unexplored. Although incentive mechanisms have been extensively studied in network and computation resource allocation, yet they cannot be applied to federated learning directly due to the unique challenges of information unsharing and difficulties of contribution evaluation. In this article, we study the incentive mechanism for federated learning to motivate edge nodes to contribute model training. Specifically, a deep reinforcement learning-based (DRL) incentive mechanism has been designed to determine the optimal pricing strategy for the parameter server and the optimal training strategies for edge nodes. Finally, numerical experiments have been implemented to evaluate the efficiency of the proposed DRL-based incentive mechanism.