Federated Learning with Only Positive Labels by Exploring Label Correlations

This approach, however, treats different labels equally Federated learning (FL) [1] is a novel machine learning in the spreadout (class embedding separation) process. That paradigm that trains an algorithm across multiple decentralized is, embeddings of class labels that are highly correlated and clients (such as edge devices) or servers without exchanging significantly different in multiple labels' space are separated in local data samples. Since clients can only access the local the same way. This is not reasonable since embeddings should datasets, the user's privacy can be well protected, and this be close for correlated labels, and dissimilar otherwise. For paradigm has attracted increasing attention in recent years [2]- example, we assume that the class labels'Desktop computer' [4]. In this paper, we study the challenge problem of learning and'Desk' often appear in the same instance, thus these two a multi-label classification model [5], [6] under the federated corresponding class embedding vectors can be deemed highcorrelation learning setting, where each user has only local positive data and may be relatively close compared with others, related to a single class label [7]. This setting can be treated such as class labels'aircraft', 'automobile', etc. Besides, since as the extremely label-skew case in the data heterogeneity of the instance and class embeddings are trained on clients and federated learning, which is popular in real-world applications.