Realizing Fully-Connected Layers Over the Air via Reconfigurable Intelligent Surfaces

2025-05-02

AI Summary

Conventional digital inference over wireless channels incurs high latency and energy consumption, especially for real-time aerial inference tasks. Method: This paper proposes AirFC—a reconfigurable intelligent surface (RIS)-assisted analog computing paradigm for over-the-air inference—where a MIMO system leverages RIS to physically realize neural network fully connected (FC) layers in the wireless channel. By jointly optimizing RIS phase shifts, transmit beamforming, and receive combining, the effective channel response approximates a target weight matrix. Contribution/Results: We introduce a novel multi-RIS cooperative architecture and a semi-closed-form weight mapping scheme, significantly enhancing channel programmability and analog computation accuracy in line-of-sight (LoS)-dominant environments. Experiments on standard benchmarks demonstrate classification accuracy comparable to digital implementations; under LoS channels, multi-RIS configurations improve performance by over 40% relative to single-RIS setups. AirFC establishes a new pathway toward ultra-low-latency, energy-efficient over-the-air intelligence.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

By leveraging the waveform superposition property of the multiple access channel, over-the-air computation (AirComp) enables the execution of digital computations through analog means in the wireless domain, leading to faster processing and reduced latency. In this paper, we propose a novel approach to implement a neural network (NN) consisting of digital fully connected (FC) layers using physically reconfigurable hardware. Specifically, we investigate reconfigurable intelligent surfaces (RISs)-assisted multiple-input multiple-output (MIMO) systems to emulate the functionality of a NN for over-the-air inference. In this setup, both the RIS and the transceiver are jointly configured to manipulate the ambient wireless propagation environment, effectively reproducing the adjustable weights of a digital FC layer. We refer to this new computational paradigm as extit{AirFC}. We formulate an imitation error minimization problem between the effective channel created by RIS and a target FC layer by jointly optimizing over-the-air parameters. To solve this non-convex optimization problem, an extremely low-complexity alternating optimization algorithm is proposed, where semi-closed-form/closed-form solutions for all optimization variables are derived. Simulation results show that the RIS-assisted MIMO-based AirFC can achieve competitive classification accuracy. Furthermore, it is also shown that a multi-RIS configuration significantly outperforms a single-RIS setup, particularly in line-of-sight (LoS)-dominated channels.

Problem

• Implementing neural networks using reconfigurable intelligent surfaces (RIS)
• Optimizing RIS-assisted MIMO systems for over-the-air inference
• Minimizing imitation error between effective channel and target FC layer

Innovation

• Leveraging RIS to emulate neural network layers
• Jointly optimizing RIS and transceiver for AirFC
• Low-complexity algorithm for non-convex optimization