Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-aided Over-the-Air Federated Learning

Abstract

Over-the-air federated learning (AirFL) allows devices to train a learning model in parallel and synchronize their local models using over-the-air computation. The integrity of AirFL is vulnerable due to the obscurity of the local models aggregated over-the-air. This paper presents a novel framework to balance the accuracy and integrity of AirFL, where multi-antenna devices and base station (BS) are jointly optimized with a reconfigurable intelligent surface (RIS). The key contributions include a new and non-trivial problem jointly considering the model accuracy and integrity of AirFL, and a new framework that transforms the problem into tractable subproblems. Under perfect channel state information (CSI), the new framework minimizes the aggregated model's distortion and retains the local models' recoverability by optimizing the transmit beamformers of the devices, the receive beamformers of the BS, and the RIS configuration in an alternating manner. Under imperfect CSI, the new framework delivers a robust design of the beamformers and RIS configuration to combat non-negligible channel estimation errors. As corroborated experimentally, the novel framework can achieve comparable accuracy to the ideal FL while preserving local model recoverability under perfect CSI, and improve the accuracy when the number of receive antennas is small or moderate under imperfect CSI.

arXiv commentThe paper has been accepted for publication in the IEEE Transactions on Wireless Communications

References in corpus (12)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Federated Learning: Challenges, Methods, and Future Directions
• Towards Smart Wireless Communications via Intelligent Reflecting Surfaces: A Contemporary Survey
• Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
• Channel Estimation for Intelligent Reflecting Surface Assisted MIMO Systems: A Tensor Modeling Approach
• MIMO Interference Alignment Over Correlated Channels with Imperfect CSI
• Energy-Efficient Joint User-RB Association and Power Allocation for Uplink Hybrid NOMA-OMA
• Nomographic Functions: Efficient Computation in Clustered Gaussian Sensor Networks
• STAR-RIS Integrated Non-Orthogonal Multiple Access and Over-the-Air Federated Learning: Framework, Analysis, and Optimization
• Energy-Efficient Power Allocation in Uplink mmWave Massive MIMO with NOMA
• Integrating Over-the-Air Federated Learning and Non-Orthogonal Multiple Access: What Role can RIS Play?
• Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devices

Cited by in corpus (5)

• Combating Interference for Over-the-Air Federated Learning: A Statistical Approach via RIS
• Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework
• Intelligent Reflecting Surfaces and Next Generation Wireless Systems
• Reconfigurable Intelligent Surface-Assisted Localization in OFDM Systems with Carrier Frequency Offset and Phase Noise
• Mixed-Precision Federated Learning via Multi-Precision Over-The-Air Aggregation