Energy-Efficient Federated Edge Learning For Small-Scale Datasets in Large IoT Networks

arXiv cs.LG / 4/14/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses how large IoT networks can achieve better learning with heterogeneous, small-scale datasets under tight energy and resource constraints at the edge.
It derives an expected learning loss to link the number of training samples with learning objectives, then uses this to guide optimization under data variation.
It proposes a stochastic online learning algorithm and formulates a resource optimization problem that includes a convergence bound.
An online distributed algorithm is introduced to solve large-scale optimization efficiently and with high scalability in federated edge settings.
Simulations and an autonomous navigation case study (collision avoidance) show improved learning performance and resource efficiency versus state-of-the-art benchmarks.

Abstract

Large-scale Internet of Things (IoT) networks enable intelligent services such as smart cities and autonomous driving, but often face resource constraints. Collecting heterogeneous sensory data, especially in small-scale datasets, is challenging, and independent edge nodes can lead to inefficient resource utilization and reduced learning performance. To address these issues, this paper proposes a collaborative optimization framework for energy-efficient federated edge learning with small-scale datasets. We first derive an expected learning loss to quantify the relationship between the number of training samples and learning objectives. A stochastic online learning algorithm is then designed to adapt to data variations, and a resource optimization problem with a convergence bound is formulated. Finally, an online distributed algorithm efficiently solves large-scale optimization problems with high scalability. Extensive simulations and autonomous navigation case studies with collision avoidance demonstrate that the proposed approach significantly improves learning performance and resource efficiency compared to state-of-the-art benchmarks.