{"id":874518,"date":"2022-09-01T00:35:03","date_gmt":"2022-09-01T07:35:03","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-blog-post&p=874518"},"modified":"2022-09-01T00:39:34","modified_gmt":"2022-09-01T07:39:34","slug":"fedx-unsupervised-federated-learning-with-cross-knowledge-distillation","status":"publish","type":"msr-blog-post","link":"https:\/\/www.microsoft.com\/en-us\/research\/articles\/fedx-unsupervised-federated-learning-with-cross-knowledge-distillation\/","title":{"rendered":"FedX: Unsupervised Federated Learning with Cross Knowledge Distillation"},"content":{"rendered":"\n
Federated learning is a new collaborative learning method that involves multiple decentralized edge devices to build a privacy-preserving shared data model without exchanging locally bound data. This technique is critical to many real-world scenarios where privacy is an issue, such as when personal data is stored on mobile devices or when patient records in hospital networks cannot be shared with central servers.<\/p>\n\n\n\n
Unsupervised learning is becoming essential in federated systems because data labels are typically scarce in practical scenarios. The fact that clients must rely on locally defined pretext tasks without ground-truth labels also adds to the complexity of the problem. For this problem, Zhang et al. proposed FedCA, a model that uses local data features and external datasets to reduce representation inconsistency [1]. Wu et al. proposed FCL that exchanges encrypted local data features for privacy and employs a neighborhood matching approach to manage decentralized client data [2]. However, these methods raise new privacy concerns because of explicit data sharing.<\/p>\n\n\n\n