FedCon: A Contrastive Framework for Federated Semi-Supervised Learning
arXiv:2109.04533
Abstract
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.
References in corpus (15)
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Bootstrap your own latent: A new approach to self-supervised Learning
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Federated Learning with Non-IID Data
- Unsupervised Data Augmentation for Consistency Training
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Federated Learning for Mobile Keyboard Prediction
- Semi-Supervised Learning with Ladder Networks
- Differentially Private Federated Learning: A Client Level Perspective
- Federated Meta-Learning with Fast Convergence and Efficient Communication
- Protection Against Reconstruction and Its Applications in Private Federated Learning
- Practical Secure Aggregation for Federated Learning on User-Held Data
- Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective