Virtual-Real Collaborated Split Learning via Model Partitioning in IRS-Assisted IoT Networks
Authors:
- Jiaying DiJDJiaying Di
- Kunlun WangKWKunlun Wang
- Jing XuJXJing Xu
- Wen ChenWen Chen
- Dusit NiyatoDNDusit Niyato
Preprint
Abstract
This paper investigates a novel computation and communication co-design framework for large-scale split learning in intelligent reflecting surface (IRS)-assisted internet of things (IoT) networks integrated with digital twin (DT) technique. The considered system consists of a multi-antenna access point (AP), multiple heterogeneous user devices (UDs), and an deployed IRS to enhance both uplink and downlink transmission. The training process of a deep neural network is partitioned between devices and the AP, where a DT replica is activated to replace UDs with insufficient local computation capabilities. We formulate a delay-optimal split learning problem, which optimizes five key variables: layer partitioning points, DT assignment decisions, IRS phase shift matrix, AP downlink power allocation, and DT frequency adjustment, aiming to minimize the overall end-to-end delay under communication and computation. The proposed optimization problem is a highly coupled non-convex mixed-integer problem. Therefore, we solve using an alternating optimization approach combining closed-form updates, semidefinite relaxation (SDR), and low-complexity heuristics. Extensive simulations demonstrate that the proposed scheme significantly reduces training delay compared to conventional baselines and achieves up to 35\% delay improvement, especially under high UD density and stringent power constraints.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- An Efficient Privacy-Aware Split Learning Framework for Satellite CommunicationsIEEE Journal on Selected Areas in Communications, 2024
- Toward Communication-Efficient Digital Twin via AI-Powered Transmission and ReconstructionIEEE Journal on Selected Areas in Communications, 2023
- Cooperative Task Offloading and Service Caching for Digital Twin Edge Networks: A Graph Attention Multi-Agent Reinforcement Learning ApproachIEEE Journal on Selected Areas in Communications, 2023
- Digital Twin for Intelligent Network: Data Lifecycle, Digital Replication, and AI-Based OptimizationsIEEE Communications Magazine, 2023
- Split Learning Over Wireless Networks: Parallel Design and Resource ManagementIEEE Journal on Selected Areas in Communications, 2023
- HiveMind: Towards Cellular Native Machine Learning Model SplittingIEEE Journal on Selected Areas in Communications, 2021
- Toward 6G Networks: Use Cases and TechnologiesIEEE Communications Magazine, 2020
- Efficient Training Management for Mobile Crowd-Machine Learning: A Deep Reinforcement Learning ApproachIEEE Wireless Communications Letters, 2019
- A Novel Two-Stage Beam Selection Algorithm in mmWave Hybrid Beamforming SystemIEEE Communications Letters, 2019
- Phase Retrieval via the Alternating Direction Method of MultipliersIEEE Signal Processing Letters, 2017