论文标题
用于任意损失和模型的多融合和未标记的学习
Multi-Complementary and Unlabeled Learning for Arbitrary Losses and Models
论文作者
论文摘要
最近提出了一个弱监督的学习框架，称为补充标签学习，每个样本都配备了一个互补标签，该标签表示样本不属于的类别之一。但是，现有的互补标签学习方法无法从易于访问的未标记的样本和具有多个互补标签的样本中学习，这些标签更具信息性。在本文中，为了消除这些局限性，我们提出了新型的多融合和未标记的学习框架，该框架允许从具有任意损失函数和模型的任何数量的互补标签和未标记的样本中对样本进行分类风险的估计。我们首先从具有多个互补标签的样品中对分类风险进行公正的估计量，然后通过将未标记的样品纳入风险配方中进一步改善估计器。估计误差边界表明所提出的方法以最佳参数收敛速率。最后，线性和深模型的实验都显示了我们方法的有效性。
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.
