AI & ML
Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models
arXiv cs.DC0 views
arXiv:2611.23908v1 Announce Type: cross 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.
Source:https://arxiv.org/abs/2611.23908PreviousAccelerating Distributed Digital Ising MachinesNextOpenGNS: An Open Dataset of the Gradient Noise Scale across Vision, Language, and Diffusion Models
Related posts
20x longer: Google's 'temporary' AI chats last 2 months
0dev.to Discuss
How I stopped guessing: confused about whether to submit a bid or a proposal and
0dev.to Discuss
Scalenut Review: Features, Pricing, Pros, Cons, and Alternatives
0dev.to Productivity
Xelta AI: The All-in-One AI Creative Platform Transforming How Content Is Created
0dev.to Productivity
How to Make AI Writing Sound More Human: A Guide to Authentic Content Creation
0dev.to Productivity
Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis
0arXiv eess.IV