CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge
Authors:
- Zhiheng GuoZGZhiheng Guo
- Zhaoyang LiuZLZhaoyang Liu
- Zihan CenZCZihan Cen
- Chenyuan FengCFChenyuan Feng
- Xinghua SunXSXinghua Sun
- Xiang ChenXCXiang Chen
- Tony Q. S. QuekTQTony Q. S. Quek
- Xijun WangXWXijun Wang
Preprint
Abstract
The deployment of large-scale neural networks within the Open Radio Access Network (O-RAN) architecture is pivotal for enabling native edge intelligence. However, this paradigm faces two critical bottlenecks: the prohibitive memory footprint required for local training on resource-constrained gNBs, and the saturation of bandwidth-limited backhaul links during the global aggregation of high-dimensional model updates. To address these challenges, we propose CoCo-Fed, a novel Compression and Combination-based Federated learning framework that unifies local memory efficiency and global communication reduction. Locally, CoCo-Fed breaks the memory wall by performing a double-dimension down-projection of gradients, adapting the optimizer to operate on low-rank structures without introducing additional inference parameters/latency. Globally, we introduce a transmission protocol based on orthogonal subspace superposition, where layer-wise updates are projected and superimposed into a single consolidated matrix per gNB, drastically reducing the backhaul traffic. Beyond empirical designs, we establish a rigorous theoretical foundation, proving the convergence of CoCo-Fed even under unsupervised learning conditions suitable for wireless sensing tasks. Extensive simulations on an angle-of-arrival estimation task demonstrate that CoCo-Fed significantly outperforms state-of-the-art baselines in both memory and communication efficiency while maintaining robust convergence under non-IID settings.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge EnvironmentsIEEE Communications Surveys & Tutorials, 2025
- Explainable AI in 6G O-RAN: A Tutorial and Survey on Architecture, Use Cases, Challenges, and Future ResearchIEEE Communications Surveys & Tutorials, 2024
- Latency-Efficient Wireless Federated Learning With Sparsification and Quantization for Heterogeneous DevicesIEEE Internet of Things Journal, 2024
- Intellicise Wireless Networks From Semantic Communications: A Survey, Research Issues, and ChallengesIEEE Communications Surveys & Tutorials, 2024
- Accurate Channel Prediction Based on Transformer: Making Mobility NegligibleIEEE Journal on Selected Areas in Communications, 2022
- Design and Analysis of Uplink and Downlink Communications for Federated LearningIEEE Journal on Selected Areas in Communications, 2020
- High-Dimensional Probability: An Introduction with Applications in Data ScienceQuantitative Finance, 2020
- Deep Anomaly Detection for Time-Series Data in Industrial IoT: A Communication-Efficient On-Device Federated Learning ApproachIEEE Internet of Things Journal, 2020
- High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning2019
- An elementary proof of a theorem of Johnson and LindenstraussRandom Structures & Algorithms, 2002