FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Long, Qianyu, Wang, Qiyuan, Anagnostopoulos, Christos, Bi, Daning
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908441649348608
author Long, Qianyu
Wang, Qiyuan
Anagnostopoulos, Christos
Bi, Daning
author_facet Long, Qianyu
Wang, Qiyuan
Anagnostopoulos, Christos
Bi, Daning
contents Federated Learning (FL), as a distributed learning paradigm, trains models over distributed clients' data. FL is particularly beneficial for distributed training of Diffusion Models (DMs), which are high-quality image generators that require diverse data. However, challenges such as high communication costs and data heterogeneity persist in training DMs similar to training Transformers and Convolutional Neural Networks. Limited research has addressed these issues in FL environments. To address this gap and challenges, we introduce a novel approach, FedPhD, designed to efficiently train DMs in FL environments. FedPhD leverages Hierarchical FL with homogeneity-aware model aggregation and selection policy to tackle data heterogeneity while reducing communication costs. The distributed structured pruning of FedPhD enhances computational efficiency and reduces model storage requirements in clients. Our experiments across multiple datasets demonstrate that FedPhD achieves high model performance regarding Fréchet Inception Distance (FID) scores while reducing communication costs by up to $88\%$. FedPhD outperforms baseline methods achieving at least a $34\%$ improvement in FID, while utilizing only $56\%$ of the total computation and communication resources.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06449
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models
Long, Qianyu
Wang, Qiyuan
Anagnostopoulos, Christos
Bi, Daning
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
68T05, 68T07, 68Q85, 94A08
I.2.6; I.2.11; C.2.4
Federated Learning (FL), as a distributed learning paradigm, trains models over distributed clients' data. FL is particularly beneficial for distributed training of Diffusion Models (DMs), which are high-quality image generators that require diverse data. However, challenges such as high communication costs and data heterogeneity persist in training DMs similar to training Transformers and Convolutional Neural Networks. Limited research has addressed these issues in FL environments. To address this gap and challenges, we introduce a novel approach, FedPhD, designed to efficiently train DMs in FL environments. FedPhD leverages Hierarchical FL with homogeneity-aware model aggregation and selection policy to tackle data heterogeneity while reducing communication costs. The distributed structured pruning of FedPhD enhances computational efficiency and reduces model storage requirements in clients. Our experiments across multiple datasets demonstrate that FedPhD achieves high model performance regarding Fréchet Inception Distance (FID) scores while reducing communication costs by up to $88\%$. FedPhD outperforms baseline methods achieving at least a $34\%$ improvement in FID, while utilizing only $56\%$ of the total computation and communication resources.
title FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
68T05, 68T07, 68Q85, 94A08
I.2.6; I.2.11; C.2.4
url https://arxiv.org/abs/2507.06449