论文标题
桥接普通标签的学习和互补标签学习
Bridging Ordinary-Label Learning and Complementary-Label Learning
论文作者
论文摘要
已经为每个培训数据提供了一个互补标签，该标签代表该模式不属于的类别。在现有文献中，对互补标签的学习进行了独立研究，该学习与普通标签学习无关，该学习假设每个训练数据都带有代表模式所属类别的标签。但是，提供补充标签应被视为等效于将所有标签作为一个真实类的候选人提供。在本文中，我们集中于以下事实：与普通标签学习和互补标签学习相对应的单一和成对分类的损失功能可以满足某些可添加性和二元性，并提供了一个直接桥接这些现有监督学习框架的框架。此外，我们为满足添加性和二元性的任何损失函数而得出分类风险和错误。
A supervised learning framework has been proposed for the situation where each training data is provided with a complementary label that represents a class to which the pattern does not belong. In the existing literature, complementary-label learning has been studied independently from ordinary-label learning, which assumes that each training data is provided with a label representing the class to which the pattern belongs. However, providing a complementary label should be treated as equivalent to providing the rest of all the labels as the candidates of the one true class. In this paper, we focus on the fact that the loss functions for one-versus-all and pairwise classification corresponding to ordinary-label learning and complementary-label learning satisfy certain additivity and duality, and provide a framework which directly bridge those existing supervised learning frameworks. Further, we derive classification risk and error bound for any loss functions which satisfy additivity and duality.
