Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

• URL: http://arxiv.org/abs/2608.25535v1
• Date: Wed, 26 Aug 2026 08:46:46 GMT
• Title: Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW
• Abstract summary: This paper proposes QEF-GT-AdamW, a communication-efficient and outage-resilient algorithm for DecL over wireless communication (WCom) networks.<n>We explicitly model the effect of bandwidth, transmit power, airtime constraints, and fading channels on DecL performance, and establish convergence guarantees for the proposed algorithm under compressed and unreliable wireless communication.
• Score: 41.35060510410376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constrained wireless links. However, existing decentralized optimization schemes often incur substantial communication overhead and degraded performance when transmissions are constrained by strict airtime budgets, fading channels, and packet losses. This paper proposes QEF-GT-AdamW, a communication-efficient and outage-resilient algorithm for DecL over wireless communication (WCom) networks. The proposed method combines gradient tracking to mitigate the effect of non-IID data, AdamW-based adaptive optimization to improve training stability, and dual-stream biased quantization with error feedback to reduce communication payloads for both model and tracking exchanges. To address unreliable broadcast communication, the proposed framework further employs a local fallback strategy when scheduled packets are not successfully received. We explicitly model the effect of bandwidth, transmit power, airtime constraints, and fading channels on DecL performance, and establish convergence guarantees for the proposed algorithm under compressed and unreliable wireless communication. Experimental results on heterogeneous MNIST and CIFAR-10 settings show that QEF-GT-AdamW consistently improves robustness and convergence performance over representative DecL baselines while achieving favorable accuracy-communication trade-offs under limited wireless resources.

Related papers

• Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data [19.70927117284918]
  In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading convergence.<n>We propose a federated random walk averaging (FedRW) framework that mitigates data heterogeneity by updating models along random walk (RW) paths and aggregating them at the server.<n>We formulate a joint optimization problem that integrates learning, RW path selection, and transmission parameter tuning, aiming to minimize the training loss under delay constraints.
  arXiv  Detail & Related papers  (2026-09-13T02:49:28Z)
• Convergence-Latency-Aware Adaptive Modulation and Resource Allocation in RIS-Assisted Wireless Federated Learning [36.8694764886586]
  Federated learning over wireless networks suffers from significant training latency and degraded convergence due to unreliable wireless transmission.<n>In this paper, we consider a wireless FL system operating under RIS-assisted blocked-link propagation scenarios.<n>By characterizing the effect of symbol errors on uploaded local gradients, we derive a convergence-related upper bound that reveals the impact of symbol error rate (SER) on FL loss decay.
  arXiv  Detail & Related papers  (2026-07-22T05:09:22Z)
• Prioritizing Gradient Sign Over Modulus: An Importance-Aware Framework for Wireless Federated Learning [72.18619424901249]
  Sign-Prioritized FL (SP-FL) is a framework that prioritizes the transmission of important gradient information through uneven resource allocation.<n>We propose an alternating optimization algorithm to solve this problem using the Newton-Raphson method and successive convex approximation (SCA)<n> Simulation results confirm the superiority of SP-FL, especially in resource-constrained scenarios.
  arXiv  Detail & Related papers  (2026-03-11T13:41:02Z)
• Straggler-Resilient Federated Learning over A Hybrid Conventional and Pinching Antenna Network [13.50794408418408]
  Leveraging pinching antennas in wireless network enabled learning (FL) can effectively mitigate the common "straggler" issue in FL.<n>A hybrid conventional and pinching antenna network (HCPAN) is proposed to significantly improve communication efficiency.
  arXiv  Detail & Related papers  (2025-08-17T17:09:42Z)
• Lightweight Federated Learning over Wireless Edge Networks [83.4818741890634]
  Federated (FL) is an alternative at network edge, but an alternative in wireless networks.<n>We derive a closed-form expression FL convergence gap transmission power, model pruning error, and quantization.<n> LTFL outperforms state-the-art schemes in experiments on real-world datasets.
  arXiv  Detail & Related papers  (2025-07-13T09:14:17Z)
• Distributionally Robust Wireless Semantic Communication with Large AI Models [111.47794569742206]
  Current SemCom systems fail to generalize across diverse noise conditions, adversarial attacks, and out-of-distribution data.<n>Wasserstein distributionally robust optimization is employed to provide resilience against semantic misinterpretation and channel perturbations.<n> Experimental results on image and text transmission demonstrate that WaSeCom achieves improved robustness under noise and adversarial perturbations.
  arXiv  Detail & Related papers  (2025-05-28T04:03:57Z)
• Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networks [55.467288506826755]
  Federated learning (FL) has been recognized as a viable solution for local-privacy-aware collaborative model training in wireless edge networks.<n>Most existing communication-efficient FL algorithms fail to reduce the significant inter-device variance.<n>We propose a novel communication-efficient FL algorithm, named FedQVR, which relies on a sophisticated variance-reduced scheme.
  arXiv  Detail & Related papers  (2025-01-20T04:26:21Z)
• Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises [18.539501941328393]
  This paper develops a latent diffusion model-enabled SemCom system to handle outliers in source data.<n>A lightweight single-layer latent space transformation adapter completes one-shot learning at the transmitter.<n>An end-to-end consistency distillation strategy is used to distill the diffusion models trained in latent space.
  arXiv  Detail & Related papers  (2024-06-09T23:39:31Z)
• Non-Coherent Over-the-Air Decentralized Gradient Descent [0.0]
  Implementing Decentralized Gradient Descent in wireless systems is challenging due to noise, fading, and limited bandwidth. This paper introduces a scalable DGD algorithm that eliminates the need for scheduling, topology information, or CSI.
  arXiv  Detail & Related papers  (2022-11-19T19:15:34Z)
• Learning Resilient Radio Resource Management Policies with Graph Neural Networks [124.89036526192268]
  We formulate a resilient radio resource management problem with per-user minimum-capacity constraints. We show that we can parameterize the user selection and power control policies using a finite set of parameters. Thanks to such adaptation, our proposed method achieves a superior tradeoff between the average rate and the 5th percentile rate.
  arXiv  Detail & Related papers  (2022-03-07T19:40:39Z)
• Federated Learning over Wireless IoT Networks with Optimized Communication and Resources [98.18365881575805]
  Federated learning (FL) as a paradigm of collaborative learning techniques has obtained increasing research attention. It is of interest to investigate fast responding and accurate FL schemes over wireless systems. We show that the proposed communication-efficient federated learning framework converges at a strong linear rate.
  arXiv  Detail & Related papers  (2021-10-22T13:25:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.