English

A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data

Machine Learning 2023-09-06 v1 Probability

Abstract

In this paper, we investigate Federated Learning (FL), a paradigm of machine learning that allows for decentralized model training on devices without sharing raw data, there by preserving data privacy. In particular, we compare two strategies within this paradigm: Federated Averaging (FedAvg) and Personalized Federated Averaging (Per-FedAvg), focusing on their performance with Non-Identically and Independently Distributed (Non-IID) data. Our analysis shows that the level of data heterogeneity, modeled using a Dirichlet distribution, significantly affects the performance of both strategies, with Per-FedAvg showing superior robustness in conditions of high heterogeneity. Our results provide insights into the development of more effective and efficient machine learning strategies in a decentralized setting.

Keywords

Cite

@article{arxiv.2309.01275,
  title  = {A Comparative Evaluation of FedAvg and Per-FedAvg Algorithms for Dirichlet Distributed Heterogeneous Data},
  author = {Hamza Reguieg and Mohammed El Hanjri and Mohamed El Kamili and Abdellatif Kobbane},
  journal= {arXiv preprint arXiv:2309.01275},
  year   = {2023}
}

Comments

6 pages, 5 figures, conference

R2 v1 2026-06-28T12:11:40.552Z