An Unbiased Risk Estimator for Learning with Augmented Classes
This paper studies the problem of learning with augmented classes (LAC), where augmented classes unobserved in the training data might emerge in the testing phase. Previous studies generally attempt to discover augmented classes by exploiting geometric properties, achieving inspiring empirical performance yet lacking theoretical understandings particularly on the generalization ability. In this paper we show that, by using unlabeled training data to approximate the potential distribution of augmented classes, an unbiased risk estimator of the testing distribution can be established for the LAC problem under mild assumptions, which paves a way to develop a sound approach with theoretical guarantees. Moreover, the proposed approach can adapt to complex changing environments where augmented classes may appear and the prior of known classes may change simultaneously. Extensive experiments confirm the effectiveness of our proposed approach.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
In contrast to the standard learning paradigm where all classes can be observed in training data, learning with augmented classes (LAC) tackles the problem where augmented classes unobserved in the training data may emer…
Multi-class ClassificationAn Unbiased Risk Estimator for Partial Label Learning with Augmented Classes
Partial Label Learning (PLL) is a typical weakly supervised learning task, which assumes each training instance is annotated with a set of candidate labels containing the ground-truth label. Recent PLL methods adopt iden…
Partial Label LearningWeakly-supervised LearningLearning from Positive and Unlabeled Data with Augmented Classes
Positive Unlabeled (PU) learning aims to learn a binary classifier from only positive and unlabeled data, which is utilized in many real-world scenarios. However, existing PU learning algorithms cannot deal with the real…
Complementary Labels Learning with Augmented Classes
Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Un…
Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
Positive--Unlabeled (PU) learning considers settings in which only positive and unlabeled data are available, while negatives are missing or left unlabeled. This situation is common in real applications where annotating …