Search papers, labs, and topics across Lattice.
This paper introduces QEF-GT-AdamW, a novel decentralized learning algorithm designed for wireless IoT networks that addresses the challenges of heterogeneous local data and communication constraints. By integrating gradient tracking, AdamW optimization, and a dual-stream biased quantization approach, the method significantly reduces communication overhead while maintaining training stability and robustness in the face of unreliable wireless conditions. Experimental results demonstrate that QEF-GT-AdamW outperforms existing decentralized learning baselines in terms of convergence and accuracy, even under stringent communication limitations.
QEF-GT-AdamW achieves superior robustness and convergence in decentralized learning over wireless networks, even when faced with severe communication constraints.
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.
