Federated learning (FL) is a distributed learning paradigm that facilitates collaborative training of a shared global model across devices while keeping data localized. The deployment of FL in numerous real-world applications faces delays, primarily due to the prevalent reliance on supervised tasks. Generating detailed labels at edge devices, if feasible, is demanding, given resource constraints and the imperative for continuous data updates. In addressing these challenges, solutions such as federated semi-supervised learning (FSSL), which relies on unlabeled clients' data and a limited amount of labeled data on the server, become pivotal. In this paper, we propose FedAnchor, an innovative FSSL method that introduces a unique double-head structure, called anchor head, paired with the classification head trained exclusively on labeled anchor data on the server. The anchor head is empowered with a newly designed label contrastive loss based on the cosine similarity metric. Our approach mitigates the confirmation bias and overfitting issues associated with pseudo-labeling techniques based on high-confidence model prediction samples. Extensive experiments on CIFAR10/100 and SVHN datasets demonstrate that our method outperforms the state-of-the-art method by a significant margin in terms of convergence rate and model accuracy.

翻译：联合学习（FL）是一种分布式学习范式，支持在设备间协作训练共享全局模型的同时保持数据的本地化。由于对监督任务的依赖，FL在众多实际应用中的部署面临延迟问题。考虑到资源约束和持续数据更新的必要性，在边缘设备上生成详细标签（即使可行）也极具挑战性。为解决这些问题，联邦半监督学习（FSSL）等方案变得至关重要——该方法依赖于无标签客户端数据及服务器上有限的带标签数据。本文提出的FedAnchor是一种创新的FSSL方法，其引入独特的双头结构（称为锚定头），与仅在服务器上使用标记锚定数据训练的分类头配对。锚定头基于余弦相似度度量，采用新设计的标签对比损失进行增强。该方法有效缓解了基于高置信度模型预测样本的伪标签技术中存在的确认偏差与过拟合问题。在CIFAR10/100和SVHN数据集上的大量实验表明，本方法在收敛速度和模型准确率方面均显著优于现有最优方法。