A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
For researchers and practitioners in federated learning, this work provides a comparative analysis of aggregation strategies, but the results are incremental and lack concrete performance numbers.
This study compares federated learning aggregation strategies under homogeneous and heterogeneous data distributions, finding that their effectiveness varies with dataset characteristics and operating conditions.
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.