High-Energy Concentration for Federated Learning in Frequency Domain

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shi, Haozhi, Xie, Weiying, Ye, Hangyu, Li, Daixun, Ma, Jitao, Li, Yunsong, Fang, Leyuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912673389608960
author Shi, Haozhi
Xie, Weiying
Ye, Hangyu
Li, Daixun
Ma, Jitao
Li, Yunsong
Fang, Leyuan
author_facet Shi, Haozhi
Xie, Weiying
Ye, Hangyu
Li, Daixun
Ma, Jitao
Li, Yunsong
Fang, Leyuan
contents Federated Learning (FL) presents significant potential for collaborative optimization without data sharing. Since synthetic data is sent to the server, leveraging the popular concept of dataset distillation, this FL framework protects real data privacy while alleviating data heterogeneity. However, such methods are still challenged by the redundant information and noise in entire spatial-domain designs, which inevitably increases the communication burden. In this paper, we propose a novel Frequency-Domain aware FL method with high-energy concentration (FedFD) to address this problem. Our FedFD is inspired by the discovery that the discrete cosine transform predominantly distributes energy to specific regions, referred to as high-energy concentration. The principle behind FedFD is that low-energy like high-frequency components usually contain redundant information and noise, thus filtering them helps reduce communication costs and optimize performance. Our FedFD is mathematically formulated to preserve the low-frequency components using a binary mask, facilitating an optimal solution through frequency-domain distribution alignment. In particular, real data-driven synthetic classification is imposed into the loss to enhance the quality of the low-frequency components. On five image and speech datasets, FedFD achieves superior performance than state-of-the-art methods while reducing communication costs. For example, on the CIFAR-10 dataset with Dirichlet coefficient $α= 0.01$, FedFD achieves a minimum reduction of 37.78\% in the communication cost, while attaining a 10.88\% performance gain.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12630
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Energy Concentration for Federated Learning in Frequency Domain
Shi, Haozhi
Xie, Weiying
Ye, Hangyu
Li, Daixun
Ma, Jitao
Li, Yunsong
Fang, Leyuan
Machine Learning
Federated Learning (FL) presents significant potential for collaborative optimization without data sharing. Since synthetic data is sent to the server, leveraging the popular concept of dataset distillation, this FL framework protects real data privacy while alleviating data heterogeneity. However, such methods are still challenged by the redundant information and noise in entire spatial-domain designs, which inevitably increases the communication burden. In this paper, we propose a novel Frequency-Domain aware FL method with high-energy concentration (FedFD) to address this problem. Our FedFD is inspired by the discovery that the discrete cosine transform predominantly distributes energy to specific regions, referred to as high-energy concentration. The principle behind FedFD is that low-energy like high-frequency components usually contain redundant information and noise, thus filtering them helps reduce communication costs and optimize performance. Our FedFD is mathematically formulated to preserve the low-frequency components using a binary mask, facilitating an optimal solution through frequency-domain distribution alignment. In particular, real data-driven synthetic classification is imposed into the loss to enhance the quality of the low-frequency components. On five image and speech datasets, FedFD achieves superior performance than state-of-the-art methods while reducing communication costs. For example, on the CIFAR-10 dataset with Dirichlet coefficient $α= 0.01$, FedFD achieves a minimum reduction of 37.78\% in the communication cost, while attaining a 10.88\% performance gain.
title High-Energy Concentration for Federated Learning in Frequency Domain
topic Machine Learning
url https://arxiv.org/abs/2509.12630