论文标题
通过间接监督信号可学习
Learnability with Indirect Supervision Signals
论文作者
论文摘要
从间接监督信号中学习在现实世界中的AI应用中很重要，当时金标签缺失或太昂贵。在本文中，当由包含带有金标签的非零互信息的变量提供监督时，我们为多类分类开发了一个统一的理论框架。该问题的性质取决于（i）从黄金标签到间接监督变量的过渡概率以及（ii）学习者对过渡的先验知识。我们的框架放松文献中的假设，并以未知，不可依赖和实例依赖性过渡支持学习。我们的理论介绍了一个名为\ emph {shipation}的新颖概念，该概念表征了可学习性和泛化界限。我们还通过具体新颖的结果来证明我们的框架的应用，以在各种学习场景中，例如使用超集注释和联合监督信号进行学习。
Learning from indirect supervision signals is important in real-world AI applications when, often, gold labels are missing or too costly. In this paper, we develop a unified theoretical framework for multi-class classification when the supervision is provided by a variable that contains nonzero mutual information with the gold label. The nature of this problem is determined by (i) the transition probability from the gold labels to the indirect supervision variables and (ii) the learner's prior knowledge about the transition. Our framework relaxes assumptions made in the literature, and supports learning with unknown, non-invertible and instance-dependent transitions. Our theory introduces a novel concept called \emph{separation}, which characterizes the learnability and generalization bounds. We also demonstrate the application of our framework via concrete novel results in a variety of learning scenarios such as learning with superset annotations and joint supervision signals.
