# Federated Learning for Diffusion Models

arXiv: https://arxiv.org/abs/2503.06426 · HTML: https://mlsanity.com/paper/2503.06426/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 49 of its 79 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 30 of 49)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning](https://mlsanity.com/paper/2101.11203/) (2021)
- [FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction](https://mlsanity.com/paper/2203.11751/) (2022)
- [Convergence of score-based generative modeling for general data distributions](https://mlsanity.com/paper/2209.12381/) (2022)
- [Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning](https://mlsanity.com/paper/2203.09249/) (2022)
- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics](https://mlsanity.com/paper/2310.13268/) (2023)
- [Federated Learning with Compression: Unified Analysis and Sharp Guarantees](https://mlsanity.com/paper/2007.01154/) (2020)
- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2306.17203/) (2023)
- [Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2106.06047/) (2021)
- [FedMix: Approximation of Mixup under Mean Augmented Federated Learning](https://mlsanity.com/paper/2107.00233/) (2021)
- [FedGAN: Federated Generative Adversarial Networks for Distributed Data](https://mlsanity.com/paper/2006.07228/) (2020)
- [Variance Reduction for Faster Non-Convex Optimization](https://mlsanity.com/paper/1603.05643/) (2016)
- [SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2309.05019/) (2023)
- [Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later](https://mlsanity.com/paper/2303.02490/) (2023)
- [Auxiliary Tasks Speed Up Learning PointGoal Navigation](https://mlsanity.com/paper/2007.04561/) (2020)
- [FedFed: Feature Distillation against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2310.05077/) (2023)
- [An improved convergence analysis for decentralized online stochastic non-convex optimization](https://mlsanity.com/paper/2008.04195/) (2020)
- [MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets](https://mlsanity.com/paper/1811.03850/) (2018)
- [FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy](https://mlsanity.com/paper/2302.10429/) (2023)

## Built on by (most cited first, 7 of 7)

- [Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models](https://mlsanity.com/paper/2508.01669/) (2025)
- [Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF](https://mlsanity.com/paper/2508.00967/) (2025)
- [Federated Flow Matching](https://mlsanity.com/paper/2509.21250/) (2025)
- [Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directions](https://mlsanity.com/paper/2603.12296/) (2026)
- [Compositional Generative Modeling from Decentralized Data](https://mlsanity.com/paper/2606.10153/) (2026)
- [Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation](https://mlsanity.com/paper/2606.22510/) (2026)
- [Regime-Aware Router Learning for Multi-Domain Medical Image Generation with Diffusion Experts](https://mlsanity.com/paper/2610.16082/) (2026)

## Abstract (arXiv)

Diffusion models are powerful generative models that can produce highly realistic samples for various tasks. Typically, these models are constructed using centralized, independently and identically distributed (IID) training data. However, in practical scenarios, data is often distributed across multiple clients and frequently manifests non-IID characteristics. Federated Learning (FL) can leverage this distributed data to train diffusion models, but the performance of existing FL methods is unsatisfactory in non-IID scenarios. To address this, we propose FedDDPM-Federated Learning with Denoising Diffusion Probabilistic Models, which leverages the data generative capability of diffusion models to facilitate model training. In particular, the server uses well-trained local diffusion models uploaded by each client before FL training to generate auxiliary data that can approximately represent the global data distribution. Following each round of model aggregation, the server further optimizes the global model using the auxiliary dataset to alleviate the impact of heterogeneous data on model performance. We provide a rigorous convergence analysis of FedDDPM and propose an enhanced algorithm, FedDDPM+, to reduce training overheads. FedDDPM+ detects instances of slow model learning and performs a one-shot correction using the auxiliary dataset. Experimental results validate that our proposed algorithms outperform the state-of-the-art FL algorithms on the MNIST, CIFAR10 and CIFAR100 datasets.