# One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models

arXiv: https://arxiv.org/abs/2311.08870 · HTML: https://mlsanity.com/paper/2311.08870/

## Key facts

- Cited by 5 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 19 of its 24 references that are in the map.
- First posted on arXiv 15 Nov 2023.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [One-Shot Federated Learning](https://mlsanity.com/paper/1902.11175/) (2019)
- [Distilled One-Shot Federated Learning](https://mlsanity.com/paper/2009.07999/) (2020)
- [DENSE: Data-Free One-Shot Federated Learning](https://mlsanity.com/paper/2112.12371/) (2021)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Federated Learning: Opportunities and Challenges](https://mlsanity.com/paper/2101.05428/) (2021)
- [Practical One-Shot Federated Learning for Cross-Silo Setting](https://mlsanity.com/paper/2010.01017/) (2020)
- [Deep Federated Learning for Autonomous Driving](https://mlsanity.com/paper/2110.05754/) (2021)
- [FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2202.13670/) (2022)
- [Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model](https://mlsanity.com/paper/2305.04063/) (2023)
- [Federated Generative Learning with Foundation Models](https://mlsanity.com/paper/2306.16064/) (2023)
- [Phoenix: A Federated Generative Diffusion Model](https://mlsanity.com/paper/2306.04098/) (2023)
- [One-shot Federated Learning without Server-side Training](https://mlsanity.com/paper/2204.12493/) (2022)

## Built on by (most cited first, 5 of 5)

- [Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning](https://mlsanity.com/paper/2409.01128/) (2024)
- [FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models](https://mlsanity.com/paper/2407.19953/) (2024)
- [Distribution Alignment for One-Shot Federated Learning via Optimal Transport](https://mlsanity.com/paper/2606.16655/) (2026)
- [Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences](https://mlsanity.com/paper/2601.03882/) (2026)
- [FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios](https://mlsanity.com/paper/2603.16370/) (2026)

## Abstract (arXiv)

In recent years, One-shot Federated Learning methods based on Diffusion Models have garnered increasing attention due to their remarkable performance. However, most of these methods require the deployment of foundation models on client devices, which significantly raises the computational requirements and reduces their adaptability to heterogeneous client models compared to traditional FL methods. In this paper, we propose FedLMG, a heterogeneous one-shot Federated learning method with Local Model-Guided diffusion models. Briefly speaking, in FedLMG, clients do not need access to any foundation models but only train and upload their local models, which is consistent with traditional FL methods. On the clients, we employ classification loss and BN loss to capture the broad category features and detailed contextual features of the client distributions. On the server, based on the uploaded client models, we utilize backpropagation to guide the server's DM in generating synthetic datasets that comply with the client distributions, which are then used to train the aggregated model. By using the locally trained client models as a medium to transfer client knowledge, our method significantly reduces the computational requirements on client devices and effectively adapts to scenarios with heterogeneous clients. Extensive quantitation and visualization experiments on three large-scale real-world datasets, along with theoretical analysis, demonstrate that the synthetic datasets generated by FedLMG exhibit comparable quality and diversity to the client datasets, which leads to an aggregated model that outperforms all compared methods and even the performance ceiling, further elucidating the significant potential of utilizing DMs in FL.