提出一种无需多轮通信的联邦无监督域适应方法，解决数据隐私与领域偏移问题。
One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labeling
- 用加权熵注意力聚合模型，优先采纳可信客户端结果
- 通过多源伪标签生成与平滑交叉熵，提升目标域标注质量
- 单次通信完成适配，适合低带宽、高隐私要求场景
联邦学习在保护隐私的协同学习中具有潜力，但面临领域偏移挑战，尤其当各客户端仅能访问自身源数据且无法共享时。现有方法常需多轮通信，导致高开销。本文提出一种单次通信的联邦无监督域适应（FUDA）方法。引入缩放熵注意力（SEA）进行模型聚合，利用目标域预测熵对可靠模型赋予更高权重，提升全局模型质量并平衡贡献。采用多源伪标签（MSPL）从多个源模型中提炼知识生成伪标签，并通过平滑软标签交叉熵（SSCE）缓解噪声标签影响。该方法在四个标准基准上优于现有最先进方法，同时显著降低通信与计算成本，适用于真实场景。代码将在发表后公开。
原文摘要 · Abstract (English)
Federated Learning (FL) is a promising approach for privacy-preserving collaborative learning. However, it faces significant challenges when dealing with domain shifts, especially when each client has access only to its source data and cannot share it during target domain adaptation. Moreover, FL methods often require high communication overhead due to multiple rounds of model updates between clients and the server. We propose a one-shot Federated Unsupervised Domain Adaptation (FUDA) method to address these limitations. Specifically, we introduce Scaled Entropy Attention (SEA) for model aggregation and Multi-Source Pseudo Labeling (MSPL) for target domain adaptation. SEA uses scaled prediction entropy on target domain to assign higher attention to reliable models. This improves the global model quality and ensures balanced weighting of contributions. MSPL distills knowledge from multiple source models to generate pseudo labels and manage noisy labels using smoothed soft-label cross-entropy (SSCE). Our approach outperforms state-of-the-art methods across four standard benchmarks while reducing communication and computation costs, making it highly suitable for real-world applications. The implementation code will be made publicly available upon publication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。