Personalized Federated Learning Techniques: Empirical Analysis

TL;DR

This paper provides an empirical analysis of ten personalized federated learning techniques, highlighting their performance trade-offs, convergence behaviors, and resource implications across diverse datasets.

Contribution

It offers a comprehensive empirical comparison of pFL methods, revealing insights into their efficiency, accuracy, and robustness in real-world scenarios.

Findings

Personalized aggregation methods converge faster due to communication efficiency.

Fine-tuning methods struggle with data heterogeneity and adversarial robustness.

Multi-objective learning achieves higher accuracy but requires more resources.

Abstract

Personalized Federated Learning (pFL) holds immense promise for tailoring machine learning models to individual users while preserving data privacy. However, achieving optimal performance in pFL often requires a careful balancing act between memory overhead costs and model accuracy. This paper delves into the trade-offs inherent in pFL, offering valuable insights for selecting the right algorithms for diverse real-world scenarios. We empirically evaluate ten prominent pFL techniques across various datasets and data splits, uncovering significant differences in their performance. Our study reveals interesting insights into how pFL methods that utilize personalized (local) aggregation exhibit the fastest convergence due to their efficiency in communication and computation. Conversely, fine-tuning methods face limitations in handling data heterogeneity and potential adversarial attacks while multi-objective learning methods achieve higher accuracy at the cost of additional training and resource consumption. Our study emphasizes the critical role of communication efficiency in scaling pFL, demonstrating how it can significantly affect resource usage in real-world deployments.