New FedMITR framework enhances one-shot federated learning for ViTs

Researchers have developed a new framework called FedMITR to improve one-shot federated learning, particularly in scenarios with highly non-independent and identically distributed (non-IID) data. This method addresses the issue of low-quality synthetic data generated by existing approaches by employing sparse model inversion to focus on meaningful image patches and avoid background noise. Additionally, FedMITR uses a token relabeling strategy for Vision Transformers (ViTs) to enhance prediction robustness by distinguishing between high and low information density patches. AI

影响 Introduces a novel framework to improve federated learning performance in challenging non-IID data scenarios, potentially enhancing privacy-preserving model training.

排序理由 Publication of a new academic paper detailing a novel framework for federated learning. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• arXiv
• FedMITR
• ViTs

• 论文
• 模型发布

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →