论文标题
通过使用标签噪声学习从标签中学习
Learning from Label Proportions by Learning with Label Noise
论文作者
论文摘要
从标签比例学习（LLP）是一个弱监督的分类问题，将数据点分组为袋子，并且观察到每个袋中的标签比例，而不是实例级别的标签。任务是学习一个分类器，以预测未来个人实例的单个标签。关于多级数据的LLP的先前工作尚未开发理论上的算法。在这项工作中，我们使用\ citet {patrini2017 -Makingdn}的前向校正（FC）丢失，基于使用标签噪声的减少来提供理论上扎根的LLP方法。我们为我们的方法建立了过多的风险约束和概括错误分析，同时还扩展了可能具有独立利益的FC损失理论。与领先的现有方法相比，我们的方法表明，在多个数据集和体系结构的深度学习方案中，经验表现得到了改善。
Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels. The task is to learn a classifier to predict the individual labels of future individual instances. Prior work on LLP for multi-class data has yet to develop a theoretically grounded algorithm. In this work, we provide a theoretically grounded approach to LLP based on a reduction to learning with label noise, using the forward correction (FC) loss of \citet{Patrini2017MakingDN}. We establish an excess risk bound and generalization error analysis for our approach, while also extending the theory of the FC loss which may be of independent interest. Our approach demonstrates improved empirical performance in deep learning scenarios across multiple datasets and architectures, compared to the leading existing methods.
