Training Diffusion Models with Federated Learning

2024-06-18 · Matthijs de Goede, Bart Cox, Jérémie Decouchant

The training of diffusion-based models for image generation is predominantly controlled by a select few Big Tech companies, raising concerns about privacy, copyright, and data authority due to their lack of transparency regarding training data. To ad-dress this issue, we propose a federated diffusion model scheme that enables the independent and collaborative training of diffusion models without exposing local data. Our approach adapts the Federated Averaging (FedAvg) algorithm to train a Denoising Diffusion Model (DDPM). Through a novel utilization of the underlying UNet backbone, we achieve a significant reduction of up to 74% in the number of parameters exchanged during training,compared to the naive FedAvg approach, whilst simultaneously maintaining image quality comparable to the centralized setting, as evaluated by the FID score.

📄 PDF Abstract BibTeX arXiv:2406.12575

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising Federated Learning Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks

2024-03-07 · Bingkun Lai, Jiayi He, Jiawen Kang, Gaolei Li 외

Generative Artificial Intelligence (GAI) shows remarkable productivity and creativity in Mobile Edge Networks, such as the metaverse and the Industrial Internet of Things. Federated learning is a promising technique for …

Diversity Federated Learning Quantization

FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning

2025-07-09 · Huan Wang, Haoran Li, Huaming Chen, Jun Yan 외 arxiv

Federated learning aims at training models collaboratively across participants while protecting privacy. However, one major challenge for this paradigm is the data heterogeneity issue, where biased data preferences acros…

Contrastive Learning Federated Learning

Federated Discrete Denoising Diffusion Model for Molecular Generation with OpenFL

2025-01-21 · Kevin Ta, Patrick Foley, Mattson Thieme, Abhishek Pandey 외

Generating unique molecules with biochemically desired properties to serve as viable drug candidates is a difficult task that requires specialized domain expertise. In recent years, diffusion models have shown promising …

Denoising Drug Design Federated Learning Privacy Preserving

FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated Diffusion Models

2024-07-20 · Jayneel Vora, Nader Bouacida, Aditya Krishnan, Prasant Mohapatra

We introduce FedDM, a novel training framework designed for the federated training of diffusion models. Our theoretical analysis establishes the convergence of diffusion models when trained in a federated setting, presen…

Quantization

Federated Learning with Diffusion Models for Privacy-Sensitive Vision Tasks

2023-11-28 · Ye Lin Tun, Chu Myaet Thwal, Ji Su Yoon, Sun Moo Kang 외

Diffusion models have shown great potential for vision-related tasks, particularly for image generation. However, their training is typically conducted in a centralized manner, relying on data collected from publicly ava…

Federated Learning Image Generation Privacy Preserving