Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models
A weakly-supervised learning framework named as complementary-label learning has been proposed recently, where each sample is equipped with a single complementary label that denotes one of the classes the sample does not belong to. However, the existing complementary-label learning methods cannot learn from the easily accessible unlabeled samples and samples with multiple complementary labels, which are more informative. In this paper, to remove these limitations, we propose the novel multi-complementary and unlabeled learning framework that allows unbiased estimation of classification risk from samples with any number of complementary labels and unlabeled samples, for arbitrary loss functions and models. We first give an unbiased estimator of the classification risk from samples with multiple complementary labels, and then further improve the estimator by incorporating unlabeled samples into the risk formulation. The estimation error bounds show that the proposed methods are in the optimal parametric convergence rate. Finally, the experiments on both linear and deep models show the effectiveness of our methods.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationImage ClassificationWeakly-supervised LearningSimilar Papers 제목 키워드 기반
Complementary-Label Learning for Arbitrary Losses and Models
In contrast to the standard classification paradigm where the true class is given to each training pattern, complementary-label learning only uses training patterns each equipped with a complementary label, which only sp…
General ClassificationImage ClassificationSurrogate Losses in Passive and Active Learning
Active learning is a type of sequential design for supervised machine learning, in which the learning algorithm sequentially requests the labels of selected instances from a large pool of unlabeled data points. The objec…
Active LearningEstimation of Soiling Losses in Unlabeled PV Data
We provide a methodology for estimating the losses due to soiling for photovoltaic (PV) systems. We focus this work on estimating the losses from historical power production data that are unlabeled, i.e. power measuremen…
Deep Latent Variable Model based Vertical Federated Learning with Flexible Alignment and Labeling Scenarios
Federated learning (FL) has attracted significant attention for enabling collaborative learning without exposing private data. Among the primary variants of FL, vertical federated learning (VFL) addresses feature-partiti…
Federated LearningVertical Federated LearningSource-Free Domain Adaptation for Real-world Image Dehazing
Deep learning-based source dehazing methods trained on synthetic datasets have achieved remarkable performance but suffer from dramatic performance degradation on real hazy images due to domain shift. Although certain Do…
Domain AdaptationImage DehazingSource-Free Domain AdaptationUnsupervised Domain Adaptation