GQ-FSL: Green Quantized Federated Split Learning

2026/07/31 by Idan Roth, Lutz Lampe
Computer Science · Engineering · #cs.DC #cs.LG #eess.SP

paper · pdf

To appear in IEEE 27th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2026

arxiv created 2026/07/31 · arxiv published 2026/07/31 · arxiv updated 2026/08/03

Abstract

Deploying state-of-the-art deep neural networks (DNNs) at the wireless edge is severely bottlenecked by the strict energy and resource constraints of mobile devices. While federated split learning (FSL) mitigates on-device computation by offloading workloads to an edge server, this may introduce systemic overheads, while the continuous exchange of cut-layer data, and submodels still incurs significant energy consumption (EC). To address this, we propose a green quantized FSL (GQ-FSL) framework that incorporates stochastic quantization for both local collaborative training and wireless transmissions. Notably, GQ-FSL supports asymmetric precision levels for the client- and server-side submodels, effectively decoupling device energy constraints from global convergence degradation. To quantify these tradeoffs, we develop parameterized energy models for the split architecture and derive a theoretical convergence bound under statistically heterogeneous data. Building on that, we formulate a joint optimization problem to configure the DNN split point and precision levels, minimizing the total system EC while satisfying a strict target accuracy constraint. Ultimately, we demonstrate that GQ-FSL enables large-scale DNN deployment on resource-constrained devices, achieving superior energy efficiency compared to quantized federated learning and full-precision FSL.

Citations

• Green Edge AI: A Contemporary Survey
• Split Learning in 6G Edge Networks
• Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks
• Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design
• Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmission
• Design and Analysis of Uplink and Downlink Communications for Federated Learning
• Communication-Computation Trade-Off in Resource-Constrained Edge Inference
• SplitFed: When Federated Learning Meets Split Learning
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• On the Convergence of FedAvg on Non-IID Data
• Minimum Energy Quantized Neural Networks
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Deep Learning with Limited Numerical Precision