Peer-to-Peer Federated Learning with Trusted Data Sharing for Non-IID Mitigation

Mahran Jazi, Irad Ben-Gal

2025

Abstract

Collaboration between edge devices without a central server defines the foundation of Peer-to-Peer Federated Learning (P2P FL), a decentralized approach to machine learning that preserves user privacy. However, P2P FL faces significant challenges when data distributions across clients are non-independent and identically distributed (non-IID), which can severely degrade learning performance. In this work, we propose an enhance-ment to P2P FL through direct data sharing between trusted peers, such as friends, colleagues, or collaborators, where each client shares a small, controlled portion of its local dataset with a selected set of neighbors. While this data-sharing mechanism enhances consistency in learning and improves model performance across the decentralized network, it introduces a trade-off between privacy and performance, as limited data sharing may increase privacy risks. To mitigate these risks, our approach assumes a trusted peer-to-peer network and avoids reliance on any central authority. We evaluate our approach using standard datasets (MNIST, CIFAR-10, and CIFAR-100) and models, including logistic regression, multilayer perceptron, convolutional neural networks (CNNs), and DenseNet-121. The results demonstrate that even modest amounts of peer data sharing significantly improve performance in non-identically distributed (non-IID) settings, offering a simple yet effective strategy to address the challenges of decentralized learning in peer-to-peer federated learning (P2P FL) systems.

Paper Citation

in Harvard Style

Jazi M. and Ben-Gal I. (2025). Peer-to-Peer Federated Learning with Trusted Data Sharing for Non-IID Mitigation. In Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN , SciTePress, pages 248-256. DOI: 10.5220/0013685100004000

in Bibtex Style

@conference{kdir25,
author={Mahran Jazi and Irad Ben-Gal},
title={Peer-to-Peer Federated Learning with Trusted Data Sharing for Non-IID Mitigation},
booktitle={Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2025},
pages={248-256},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013685100004000},
isbn={},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Peer-to-Peer Federated Learning with Trusted Data Sharing for Non-IID Mitigation
SN -
AU - Jazi M.
AU - Ben-Gal I.
PY - 2025
SP - 248
EP - 256
DO - 10.5220/0013685100004000
PB - SciTePress