cs.AINov 18, 2026

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

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

Organizations: Northeastern University, China · Hong Kong University of Science and Technology, China · University of Macau, China

Abstract

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.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Distribution Alignment for One-Shot Federated Learning via Optimal Transport

    Jun 15, 2026Daniele Berardini, Vito Paolo Pastore, Vittorio MurinoDistribution MatchingOptimal Transport

  2. CRIP: Channel Level Representation Injection for Personalized One-Shot Federated Learning

    Aug 3, 2026Zijian Jiang, Chaoli Sun, Handing Wang +1Non-IID Federated LearningRepresentation Alignment

  3. Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

    Jul 8, 2026Maximilian Andreas Hoefler, Karsten Mueller, Wojciech SamekNon-IID Federated LearningFederated Learning