无标签数据下联邦学习实现跨域分类，兼顾隐私与性能
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data
- 通过加权聚类聚合客户端模型，避免使用源域标签
- 在多个目标域上实现优于基线的分类准确率
- 适合缺乏标注数据且重视隐私保护的场景
联邦学习通常假设服务器或部分客户端拥有标注数据，但实际中因标注成本和隐私问题难以满足。本文针对一种无需源域标签的联邦源域自适应任务（即联邦源域自适应，FFREEDA），提出一种新的加权聚类聚合方法（FedWCA）。该方法适用于分类任务，而此前研究仅限于语义分割。具体而言，服务器持有源域训练好的预训练模型，各客户端仅拥有来自不同目标域的无标签数据，且在适配阶段无法访问源域数据。FedWCA包含三个阶段：客户端私有且无参数的聚类以生成领域特定的全局模型；对聚类后客户端的全局模型进行加权聚合；结合伪标签进行本地域自适应。实验表明，该方法在多个目标域上均优于现有方法与基线，验证了其有效性与实用性。
原文摘要 · Abstract (English)
Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this problem, we focus on a source-free domain adaptation task, where (1) the server holds a pre-trained model on labeled source domain data, (2) clients possess only unlabeled data from various target domains, and (3) the server and clients cannot access the source data in the adaptation phase. This task is known as Federated source-Free Domain Adaptation (FFREEDA). Specifically, we focus on classification tasks, while the previous work solely studies semantic segmentation. Our contribution is the novel Federated learning with Weighted Cluster Aggregation (FedWCA) method, designed to mitigate both domain shifts and privacy concerns with only unlabeled data. FedWCA comprises three phases: private and parameter-free clustering of clients to obtain domain-specific global models on the server, weighted aggregation of the global models for the clustered clients, and local domain adaptation with pseudo-labeling. Experimental results show that FedWCA surpasses several existing methods and baselines in FFREEDA, establishing its effectiveness and practicality.
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。