Adaptive Federated Learning in Resource Constrained Edge Computing Systems

TL;DR

This paper addresses resource-efficient federated learning at the network edge by analyzing convergence and proposing a control algorithm to optimize local and global updates, validated through extensive experiments.

Contribution

It introduces a theoretical convergence analysis and a novel control algorithm for adaptive federated learning in resource-constrained edge systems.

Findings

The proposed algorithm achieves near-optimal performance across various models.

Experimental results validate effectiveness on real and simulated environments.

The approach balances local updates and global aggregation to minimize resource use.

Abstract

Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. In this paper, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of machine learning models that are trained using gradient-descent based approaches. We analyze the convergence bound of distributed gradient descent from a theoretical point of view, based on which we propose a control algorithm that determines the best trade-off between local update and global parameter aggregation to minimize the loss function under a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real datasets, both on a networked prototype system and in a larger-scale simulated environment. The experimentation results show that our proposed approach performs near to the optimum with various machine learning models and different data distributions.