PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Liangyan, Liu, Yangyi, Ning, Yimo, Rini, Stefano, Chen, Jun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916800481984512
author Li, Liangyan
Liu, Yangyi
Ning, Yimo
Rini, Stefano
Chen, Jun
author_facet Li, Liangyan
Liu, Yangyi
Ning, Yimo
Rini, Stefano
Chen, Jun
contents Federated Learning (FL) has emerged as a powerful paradigm for leveraging diverse datasets from multiple sources while preserving data privacy by avoiding centralized storage. However, many existing approaches fail to account for the intricate gradient correlations between remote clients, a limitation that becomes especially problematic in data heterogeneity scenarios. In this work, we propose a novel FL framework utilizing Power-Norm Cosine Similarity (PNCS) to improve client selection for model aggregation. By capturing higher-order gradient moments, PNCS addresses non-IID data challenges, enhancing convergence speed and accuracy. Additionally, we introduce a simple algorithm ensuring diverse client selection through a selection history queue. Experiments with a VGG16 model across varied data partitions demonstrate consistent improvements over state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learning
Li, Liangyan
Liu, Yangyi
Ning, Yimo
Rini, Stefano
Chen, Jun
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Federated Learning (FL) has emerged as a powerful paradigm for leveraging diverse datasets from multiple sources while preserving data privacy by avoiding centralized storage. However, many existing approaches fail to account for the intricate gradient correlations between remote clients, a limitation that becomes especially problematic in data heterogeneity scenarios. In this work, we propose a novel FL framework utilizing Power-Norm Cosine Similarity (PNCS) to improve client selection for model aggregation. By capturing higher-order gradient moments, PNCS addresses non-IID data challenges, enhancing convergence speed and accuracy. Additionally, we introduce a simple algorithm ensuring diverse client selection through a selection history queue. Experiments with a VGG16 model across varied data partitions demonstrate consistent improvements over state-of-the-art methods.
title PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learning
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2506.15923