FedCon: A Contrastive Framework for Federated Semi-Supervised Learning
It addresses a practical limitation in federated learning for scenarios where clients lack incentives to provide labels, offering a solution for real-world applications.
The paper tackles the problem of federated semi-supervised learning where labels are stored at the server side, a practical scenario not handled by existing methods, and proposes FedCon, which achieves the best performance on three datasets under IID and Non-IID settings.
Federated Semi-Supervised Learning (FedSSL) has gained rising attention from both academic and industrial researchers, due to its unique characteristics of co-training machine learning models with isolated yet unlabeled data. Most existing FedSSL methods focus on the classical scenario, i.e, the labeled and unlabeled data are stored at the client side. However, in real world applications, client users may not provide labels without any incentive. Thus, the scenario of labels at the server side is more practical. Since unlabeled data and labeled data are decoupled, most existing FedSSL approaches may fail to deal with such a scenario. To overcome this problem, in this paper, we propose FedCon, which introduces a new learning paradigm, i.e., contractive learning, to FedSSL. Experimental results on three datasets show that FedCon achieves the best performance with the contractive framework compared with state-of-the-art baselines under both IID and Non-IID settings. Besides, ablation studies demonstrate the characteristics of the proposed FedCon framework.