A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions

2026-05-10

AI Summary

This study systematically investigates the impact of aggregation strategies on model performance, robustness, and system efficiency in federated learning under diverse data distributions. Within a unified experimental framework, the authors evaluate multiple state-of-the-art aggregation algorithms across both homogeneous and heterogeneous data settings, using several standard image classification benchmarks. By comprehensively analyzing metrics including model accuracy, convergence loss, and communication overhead, the work elucidates the strengths, limitations, and operational boundaries of each aggregation approach. The findings provide empirical insights and practical design guidelines for selecting and deploying aggregation strategies in real-world federated learning systems.

Abstract

Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy used to combine local model updates at the server, which directly affects learning performance, robustness, and system behavior. This work presents a comprehensive experimental comparison of widely used federated aggregation strategies under both homogeneous and heterogeneous data distributions. Using benchmark image classification datasets, we analyze how different aggregation mechanisms respond to varying degrees of data heterogeneity, examining their impact on centralized accuracy and loss, and system-level efficiency metrics, including aggregation, training, and communication time. The results demonstrate that aggregation strategies exhibit distinct trade-offs across datasets and data distributions, with their effectiveness varying according to dataset characteristics and operating conditions.

Problem

• Federated Learning
• Aggregation Strategies
• Data Heterogeneity
• Homogeneous Data
• Model Performance

Innovation

• Federated Learning
• Aggregation Strategies
• Data Heterogeneity
• System Efficiency
• Empirical Evaluation