Optimization of Federated Learning's Client Selection for Non-IID Data Based on Grey Relational Analysis

TL;DR

This paper introduces a client selection method for federated learning based on Grey Relational Analysis, which considers data distribution and resources to improve efficiency and accuracy under non-IID data conditions.

Contribution

The paper presents a novel client selection approach using GRA that accounts for data heterogeneity and resource availability, enhancing federated learning performance.

Findings

Improved test accuracy over state-of-the-art methods.

Reduced client's waiting time during training.

Enhanced training efficiency in non-IID data scenarios.

Abstract

Federated learning (FL) is a novel distributed learning framework designed for applications with privacy-sensitive data. Without sharing data, FL trains local models on individual devices and constructs the global model on the server by performing model aggregation. However, to reduce the communication cost, the participants in each training round are randomly selected, which significantly decreases the training efficiency under data and device heterogeneity. To address this issue, in this paper, we introduce a novel approach that considers the data distribution and computational resources of devices to select the clients for each training round. Our proposed method performs client selection based on the Grey Relational Analysis (GRA) theory by considering available computational resources for each client, the training loss, and weight divergence. To examine the usability of our proposed method, we implement our contribution on Amazon Web Services (AWS) by using the TensorFlow library of Python. We evaluate our algorithm's performance in different setups by varying the learning rate, network size, the number of selected clients, and the client selection round. The evaluation results show that our proposed algorithm enhances the performance significantly in terms of test accuracy and the average client's waiting time compared to state-of-the-art methods, federated averaging and Pow-d.