The proliferation of edge devices has brought Federated Learning (FL) to the forefront as a promising paradigm for decentralized and collaborative model training while preserving the privacy of clients' data. However, FL struggles with a significant performance reduction and poor convergence when confronted with Non-Independent and Identically Distributed (Non-IID) data distributions among participating clients. While previous efforts, such as client drift mitigation and advanced server-side model fusion techniques, have shown some success in addressing this challenge, they often overlook the root cause of the performance reduction - the absence of identical data accurately mirroring the global data distribution among clients. In this paper, we introduce Gen-FedSD, a novel approach that harnesses the powerful capability of state-of-the-art text-to-image foundation models to bridge the significant Non-IID performance gaps in FL. In Gen-FedSD, each client constructs textual prompts for each class label and leverages an off-the-shelf state-of-the-art pre-trained Stable Diffusion model to synthesize high-quality data samples. The generated synthetic data is tailored to each client's unique local data gaps and distribution disparities, effectively making the final augmented local data IID. Through extensive experimentation, we demonstrate that Gen-FedSD achieves state-of-the-art performance and significant communication cost savings across various datasets and Non-IID settings.

翻译：边缘设备的普及使得联邦学习成为一种有前途的去中心化协作模型训练范式，同时能够保护客户数据的隐私。然而，当参与客户之间的数据分布呈现非独立同分布时，联邦学习会面临显著的性能下降和收敛困难问题。尽管先前的研究尝试通过客户端漂移缓解和高级服务器端模型融合技术来解决这一挑战，并取得了一定成效，但这些方法往往忽略了性能下降的根本原因——客户端缺乏能准确反映全局数据分布的相同数据。在本文中，我们提出Gen-FedSD，一种利用最先进的文本到图像基础模型的强大能力来弥合联邦学习中非独立同分布性能差距的新方法。在Gen-FedSD中，每个客户端为每个类别标签构建文本提示，并利用现成的最先进预训练稳定扩散模型合成高质量数据样本。生成的合成数据针对每个客户端独特的本地数据缺口和分布差异进行定制，有效使最终增强后的本地数据满足独立同分布条件。通过大量实验，我们证明Gen-FedSD在多种数据集和非独立同分布设置下实现了最先进的性能并显著节省了通信成本。