arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2611.23908cs.AIcs.CVcs.DC
收藏

基于服务器端预训练扩散模型的单样本联邦学习无训练域生成

Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models

Northeastern University(东北大学);Hong Kong University of Science and Technology(香港科技大学);University of Macau(澳门大学)

Yixuan Tong, Yuanguo Bi, Mingjian Zhi, Wenchao Xu, Yuan Wu

AI总结:

针对单样本联邦学习中异构客户端分布学习难的问题,提出FedDoG无训练域生成框架,利用服务器端预训练扩散模型合成对齐客户端域的数据,大幅降低客户端成本且性能优于基线。

摘要:

单样本联邦学习(OSFL)因能通过将客户端-服务器交互限制为单轮通信大幅降低通信开销而受到越来越多关注。然而,这种有限的交互使得从异构客户端分布中学习颇具挑战性。基于扩散的OSFL方法试图通过合成近似客户端分布的数据来应对这一挑战,但现有方法往往给客户端带来巨大计算成本,且缺乏有效视觉引导以生成与客户端分布对齐的数据。为解决这些局限,我们提出FedDoG,一种无训练域生成框架,利用服务器端预训练扩散模型合成与客户端域对齐的数据。FedDoG通过冻结图像编码器提取紧凑域表示,大幅降低客户端侧计算与通信成本;这些表示经预训练图像条件适配器融入扩散模型,为域生成提供显式视觉引导。为进一步提升合成数据质量,FedDoG根据域浓度调整视觉条件强度,并基于类别一致性与预测熵过滤生成样本。在三个基准上的实验表明,FedDoG生成更高质量的合成图像,在分类准确率上优于现有OSFL基线,同时将客户端上传与计算时间分别降低99.9%与91.5%。代码可在该https URL获取。

英文摘要:

One-shot federated learning (OSFL) has attracted increasing attention for its ability to substantially reduce communication overhead by limiting client-server interaction to a single communication round. Nevertheless, this limited interaction makes learning from heterogeneous client distributions challenging. Diffusion-based OSFL approaches seek to address this challenge by synthesizing data that approximate client distributions. However, existing diffusion-based approaches often impose substantial computational costs on clients and lack effective visual guidance to generate data aligned with client distributions. To address these limitations, we propose FedDoG, a training-free Domain Generation framework that leverages server-side pre-trained diffusion models to synthesize data aligned with client domains. FedDoG extracts compact domain representations using a frozen image encoder, substantially reducing client-side computational and communication costs. These representations are incorporated into the diffusion model through a pre-trained image-conditioning adapter, thereby providing explicit visual guidance for domain generation. To further improve the quality of synthetic data, FedDoG adapts the strength of visual conditioning according to domain concentration and filters generated samples based on class consistency and predictive entropy. Experiments on three benchmarks demonstrate that FedDoG generates higher-quality synthetic images and outperforms existing OSFL baselines in classification accuracy. Meanwhile, FedDoG reduces client upload and computation time by 99.9% and 91.5%, respectively. The code is available at https://github.com/YXTong17/FedDoG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑