{"ID":2823188,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00549","arxiv_id":"2601.00549","title":"CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge","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.","short_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 o...","url_abs":"https://arxiv.org/abs/2601.00549","url_pdf":"https://arxiv.org/pdf/2601.00549v1","authors":"[\"Zhiheng Guo\",\"Zhaoyang Liu\",\"Zihan Cen\",\"Chenyuan Feng\",\"Xinghua Sun\",\"Xiang Chen\",\"Tony Q. S. Quek\",\"Xijun Wang\"]","published":"2026-01-02T03:39:50Z","proceeding":"cs.IT","tasks":"[\"cs.IT\",\"cs.AI\"]","methods":"[]","has_code":false}