Over-the-Air Split Machine Learning in Wireless MIMO Networks

2022/10/07 by Yuzhi Yang, Yang, Yuzhi, Zhaoyang Zhang +11 · 4 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning (cs.LG) #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.2210.04742

openalex publication_date 2022/10/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In split machine learning (ML), different partitions of a neural network (NN) are executed by different computing nodes, requiring a large amount of communication cost. To ease communication burden, over-the-air computation (OAC) can efficiently implement all or part of the computation at the same time of communication. Based on the proposed system, the system implementation over wireless network is introduced and we provide the problem formulation. In particular, we show that the inter-layer connection in a NN of any size can be mathematically decomposed into a set of linear precoding and combining transformations over MIMO channels. Therefore, the precoding matrix at the transmitter and the combining matrix at the receiver of each MIMO link, as well as the channel matrix itself, can jointly serve as a fully connected layer of the NN. The generalization of the proposed scheme to the conventional NNs is also introduced. Finally, we extend the proposed scheme to the widely used convolutional neural networks and demonstrate its effectiveness under both the static and quasi-static memory channel conditions with comprehensive simulations. In such a split ML system, the precoding and combining matrices are regarded as trainable parameters, while MIMO channel matrix is regarded as unknown (implicit) parameters.

Cited by

• Bayes-Split-Edge: Bayesian Optimization for Constrained Collaborative Inference in Wireless Edge Systems
• Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces
• Optimizing Model Splitting and Device Task Assignment for Deceptive Signal Assisted Private Multi-hop Split Learning
• A New Pathway to Integrated Learning and Communication (ILAC): Large AI Model and Hyperdimensional Computing for Communication

Related

• Over-the-Air Split Learning with MIMO-Based Neural Network and Constellation-Based Activation
• Over-the-Air Inference over Multi-hop MIMO Networks
• Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces
• SplitMAC: Wireless Split Learning over Multiple Access Channels
• Accelerating Split Federated Learning over Wireless Communication Networks