用对比样本提升主动学习效率，理论揭示其降本增效机制
Formal Models of Active Learning from Contrastive Examples
- 构建对比样本主动学习的理论框架，分析其对学习复杂度的影响
- 证明合理选择对比样本可显著降低学习所需数据量
- 连接经典自导向学习模型，为高效学习提供新视角
机器学习可从提供成对对比训练样本中获益——即仅在细微差异下标签不同的实例对。直观上，实例间的差异有助于解释标签差异。本文提出一个理论框架，形式化研究不同类型的对比样本对主动学习者的影响，重点分析概念类的学习样本复杂度如何受对比样本选择的影响。通过几何概念类和布尔函数类进行验证。有趣的是，我们揭示了从对比样本学习与经典自导向学习模型之间的联系。
原文摘要 · Abstract (English)
Machine learning can greatly benefit from providing learning algorithms with pairs of contrastive training examples -- typically pairs of instances that differ only slightly, yet have different class labels. Intuitively, the difference in the instances helps explain the difference in the class labels. This paper proposes a theoretical framework in which the effect of various types of contrastive examples on active learners is studied formally. The focus is on the sample complexity of learning concept classes and how it is influenced by the choice of contrastive examples. We illustrate our results with geometric concept classes and classes of Boolean functions. Interestingly, we reveal a connection between learning from contrastive examples and the classical model of self-directed learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。