Robust Segmented Analog Broadcast Design to Accelerate Wireless Federated Learning

2025-10-02

AI Summary

To address high downlink broadcast latency in wireless federated learning (FL) under imperfect channel state information (CSI), this paper proposes Segmented Analog Broadcasting (SegAB). SegAB partitions the global model parameters and concurrently maps them to the analog domain for multi-antenna beamforming transmission. We formulate a novel robust beamforming optimization framework designed per training round based on worst-case performance, eliminating the need for future CSI prediction and ensuring monotonic convergence of FL training. The method integrates segmented analog transmission, robust beamforming design, CSI error modeling, upper-bound relaxation, and dual decomposition. Experimental results in representative wireless environments demonstrate that SegAB significantly reduces downlink transmission latency: it accelerates convergence by 30%–50% compared to conventional full-model digital broadcasting and state-of-the-art alternatives.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We consider downlink broadcast design for federated learning (FL) in a wireless network with imperfect channel state information (CSI). Aiming to reduce transmission latency, we propose a segmented analog broadcast (SegAB) scheme, where the parameter server, hosted by a multi-antenna base station, partitions the global model parameter vector into segments and transmits multiple parameters from these segments simultaneously over a common downlink channel. We formulate the SegAB transmission and reception processes to characterize FL training convergence, capturing the effects of downlink beamforming and imperfect CSI. To maximize the FL training convergence rate, we establish an upper bound on the expected model optimality gap and show that it can be minimized separately over the training rounds in online optimization, without requiring knowledge of the future channel states. We solve the per-round problem to achieve robust downlink beamforming, by minimizing the worst-case objective via an epigraph representation and a feasibility subproblem that ensures monotone convergence. Simulation with standard classification tasks under typical wireless network setting shows that the proposed SegAB substantially outperforms conventional full-model per-parameter broadcast and other alternatives.

Problem

• Designing robust analog broadcast for wireless federated learning
• Minimizing transmission latency with segmented parameter transmission
• Achieving robust beamforming under imperfect channel state information

Innovation

• Segmented analog broadcast reduces transmission latency
• Robust downlink beamforming maximizes convergence rate
• Epigraph representation solves per-round optimization problem