Multi-Class Classification from Single-Class Data with Confidences

Abstract

Can we learn a multi-class classifier from only data of a single class? We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i.e., the class-posterior probabilities for all the classes) are available. Specifically, we propose an empirical risk minimization framework that is loss-/model-/optimizer-independent. Instead of constructing a boundary between the given class and other classes, our method can conduct discriminative classification between all the classes even if no data from the other classes are provided. We further theoretically and experimentally show that our method can be Bayes-consistent with a simple modification even if the provided confidences are highly noisy. Then, we provide an extension of our method for the case where data from a subset of all the classes are available. Experimental results demonstrate the effectiveness of our methods.

Learning with Proper Partial Labels

“…Candidate Label Confidence. Various weakly supervised learning settings based on confidence data have been studied recently, including positive-confidence data [Ishida et al, 2018], similarityconfidence data [Cao et al, 2021b], confidence data for instance-dependent label-noise [Berthon et al, 2021] and single-class confidence [Cao et al, 2021a]. Here, we propose the following candidate label confidence:…”