arXiv Machine Learning August 27, 2026 By Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi, Vu Nguyen Ha, Symeon Chatzinotas

Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

Read the original on arXiv Machine Learning →

The paper introduces QEF-GT-AdamW, a communication‑efficient and outage‑resilient algorithm for decentralized wireless federated learning. It combines gradient tracking, AdamW adaptive optimization, and dual‑stream biased quantization with error feedback to reduce communication payloads while mitigating non‑IID data effects. The method includes a local fallback strategy for unreliable broadcasts and provides convergence guarantees under compressed, unreliable wireless communication, demonstrating improved robustness and accuracy‑communication trade‑offs on heterogeneous MNIST and CIFAR‑10 datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

efficiency

Hugging Face Trending Papers

Aug 26

Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

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...

efficiency

arXiv Machine Learning

Jun 17

Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation

arXiv:2606. 10774v2 Announce Type: replace Abstract: Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations.

By Chanuka A. S. Hewa Kaluannakkage, Rajkumar Buyya

agents benchmarks safety

arXiv Machine Learning

Sep 15

Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data

arXiv:2609.14246v1 Announce Type: cross Abstract: In wireless federated learning (FL), data heterogeneity and multiple local updates induce client drift, degrading model convergence. It is further af...

By Changheng Wang, Xianchao Zhang, Zhiqing Wei, Lingzhu Zhao, Zhongming Yang, Zhiyong Feng

efficiency benchmarks

arXiv AI

Aug 11

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

arXiv:2608. 09208v1 Announce Type: cross Abstract: Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL).

By Van Truong Vo, Khoa Nguyen, Taehong Kim

arXiv Machine Learning

Jun 10

Inverse Probability Weighting and Age-of-Information Aggregation for Decentralized Federated Learning under Partial Reception

arXiv:2606. 10774v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) over lossy wireless networks faces two key challenges: selection bias, where updates from poor-quality links are systematically underrepresented due to partial model reception, and update staleness, where asynchronous nodes contribute outdated information.

By Chanuka A. S. Hewa Kaluannakkage, Rajkumar Buyya

benchmarks safety

Hugging Face Trending Papers

Aug 10

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL). However, DFL suffers from convergence inefficiency under data heterogeneity due to the use of a uniform learning rate (LR) that ignores layer-specific optimization needs.

One email a morning, machine-written

Related stories

Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation

Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Data

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning

Inverse Probability Weighting and Age-of-Information Aggregation for Decentralized Federated Learning under Partial Reception

FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning