In recent years, the attention towards One-Shot Federated Learning (OSFL) has been driven by its capacity to minimize communication. With the development of the diffusion model (DM), several methods employ the DM for OSFL, utilizing model parameters, image features, or textual prompts as mediums to transfer the local client knowledge to the server. However, these mediums often require public datasets or the uniform feature extractor, significantly limiting their practicality. In this paper, we propose FedDEO, a Description-Enhanced One-Shot Federated Learning Method with DMs, offering a novel exploration of utilizing the DM in OSFL. The core idea of our method involves training local descriptions on the clients, serving as the medium to transfer the knowledge of the distributed clients to the server. Firstly, we train local descriptions on the client data to capture the characteristics of client distributions, which are then uploaded to the server. On the server, the descriptions are used as conditions to guide the DM in generating synthetic datasets that comply with the distributions of various clients, enabling the training of the aggregated model. Theoretical analyses and sufficient quantitation and visualization experiments on three large-scale real-world datasets demonstrate that through the training of local descriptions, the server is capable of generating synthetic datasets with high quality and diversity. Consequently, with advantages in communication and privacy protection, the aggregated model outperforms compared FL or diffusion-based OSFL methods and, on some clients, outperforms the performance ceiling of centralized training.

翻译：近年来，单次联邦学习因其能够最小化通信开销而受到广泛关注。随着扩散模型的发展，已有若干方法将其应用于单次联邦学习，利用模型参数、图像特征或文本提示作为媒介，将本地客户端知识传递至服务器。然而，这些媒介通常需要公共数据集或统一的特征提取器，极大地限制了其实用性。本文提出FedDEO，一种基于扩散模型的描述增强单次联邦学习方法，为在单次联邦学习中利用扩散模型提供了新的探索。本方法的核心思想是在客户端训练本地描述，将其作为将分布式客户端知识传递至服务器的媒介。首先，我们在客户端数据上训练本地描述以捕捉客户端分布的特征，随后将其上传至服务器。在服务器端，这些描述被用作条件来指导扩散模型生成符合各客户端分布的合成数据集，从而训练聚合模型。在三个大规模真实数据集上的理论分析及充分的定量与可视化实验表明，通过本地描述的训练，服务器能够生成高质量、高多样性的合成数据集。因此，在通信与隐私保护方面具有优势的聚合模型，其性能超越了现有的联邦学习或基于扩散的单次联邦学习方法，并在部分客户端上超越了集中式训练的性能上限。