信息减法：学习用于条件熵的表示
Information Subtraction: Learning Representations for Conditional Entropy
AI总结：
本文提出 Information Subtraction 框架，通过同时最大化和最小化信息项学习解耦表示，将条件信息移除扩展到连续变量，并在公平学习与领域泛化中验证有效。
摘要：
条件熵和条件互信息的表示对于解释变量之间的独特效应具有重要意义。尽管以往基于条件对比采样的研究已经有效移除了关于离散敏感变量的信息，但其范围尚未扩展到连续情形。本文提出 Information Subtraction（信息减法），这是一个旨在生成保留所需信息同时消除不需要信息的表示的框架。我们实现了一种基于生成的架构，通过同时最大化一个信息项并最小化另一个信息项来输出这些表示。凭借其在解耦信息方面的灵活性，我们可以迭代应用 Information Subtraction 来表示连续变量之间的任意信息成分，从而解释它们之间存在的各种关系。我们的结果突显了这些表示提供条件熵语义特征的能力。通过减去敏感信息和特定领域信息，我们的框架在公平学习和领域泛化中展示了有效的性能。本文代码可在 https://github.com/jh-liang/Information-Subtraction 获取。
英文摘要：
The representations of conditional entropy and conditional mutual information are significant in explaining the unique effects among variables. While previous studies based on conditional contrastive sampling have effectively removed information regarding discrete sensitive variables, they have not yet extended their scope to continuous cases. This paper introduces Information Subtraction, a framework designed to generate representations that preserve desired information while eliminating the undesired. We implement a generative-based architecture that outputs these representations by simultaneously maximizing an information term and minimizing another. With its flexibility in disentangling information, we can iteratively apply Information Subtraction to represent arbitrary information components between continuous variables, thereby explaining the various relationships that exist between them. Our results highlight the representations' ability to provide semantic features of conditional entropy. By subtracting sensitive and domain-specific information, our framework demonstrates effective performance in fair learning and domain generalization. The code for this paper is available at https://github.com/jh-liang/Information-Subtraction
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
