Integrating Over-the-Air Federated Learning and Non-Orthogonal Multiple Access: What Role can RIS Play?

Abstract

With the aim of integrating over-the-air federated learning (AirFL) and non-orthogonal multiple access (NOMA) into an on-demand universal framework, this paper proposes a novel reconfigurable intelligent surface (RIS)-aided hybrid network by leveraging the RIS to flexibly adjust the signal processing order of heterogeneous data. The objective of this work is to maximize the achievable hybrid rate by jointly optimizing the transmit power, controlling the receive scalar, and designing the phase shifts. Since the concurrent transmissions of all computation and communication signals are aided by the discrete phase shifts at the RIS, the considered problem (P0) is a challenging mixed integer programming problem. To tackle this intractable issue, we decompose the original problem (P0) into a non-convex problem (P1) and a combinatorial problem (P2), which are characterized by the continuous and discrete variables, respectively. For the transceiver design problem (P1), the power allocation subproblem is first solved by invoking the difference-of-convex programming, and then the receive control subproblem is addressed by using the successive convex approximation, where the closed-form expressions of simplified cases are derived to obtain deep insights. For the reflection design problem (P2), the relaxation-then-quantization method is adopted to find a suboptimal solution for striking a trade-off between complexity and performance. Afterwards, an alternating optimization algorithm is developed to solve the non-linear and non-convex problem (P0) iteratively. Finally, simulation results reveal that 1) the proposed RIS-aided hybrid network can support the on-demand communication and computation efficiently, 2) the performance gains can be improved by properly selecting the location of the RIS, and 3) the designed algorithms are also applicable to conventional networks with only AirFL or NOMA users.

This paper has been accepted by IEEE Transactions on Wireless Communications

References in corpus (2)

• Sum Rate Maximization for IRS-assisted Uplink NOMA
• Federated Learning: A Signal Processing Perspective

Cited by in corpus (12)

• Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing
• Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures
• STAR-RIS Integrated Non-Orthogonal Multiple Access and Over-the-Air Federated Learning: Framework, Analysis, and Optimization
• Semi-Federated Learning for Collaborative Intelligence in Massive IoT Networks
• Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-aided Over-the-Air Federated Learning
• Federated Deep Reinforcement Learning for RIS-Assisted Indoor Multi-Robot Communication Systems
• Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Framework
• Convergence Analysis and Latency Minimization for Semi-Federated Learning in Massive IoT Networks
• Reconfigurable Intelligent Surface for Internet of Robotic Things
• Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
• Simultaneous Computation and Communication over MAC
• QoS-Constrained Federated Learning Empowered by Intelligent Reflecting Surface