论信息论公平性:具有完美人口统计平价的压缩表示
On Information Theoretic Fairness: Compressed Representations With Perfect Demographic Parity
AI总结:
本文从信息论视角研究设计具有完美人口统计平价和隐私的表示的基本极限,通过扩展 Functional Representation Lemma 等工具,在约束压缩率或无关信息的条件下最大化任务相关信息,并证明了所得界限的紧致性。
摘要:
在本文中,我们通过信息论的视角,研究了设计实现完美人口统计平价和/或完美隐私的公平和/或私有表示的基本极限。更准确地说,给定一些我们希望用于解决任务 $T$ 的有用数据 $X$,我们考虑设计一种表示 $Y$,使其不包含某些敏感属性或秘密 $S$ 的信息,即满足 $I(Y;S) = 0$。我们考虑两种场景。首先,我们考虑一种设计期望,即我们希望最大化表示中包含的关于任务的信息 $I(Y;T)$,同时约束压缩水平(或编码率),即确保 $I(Y;X) \leq r$。其次,受 Conditional Fairness Bottleneck 问题的启发,我们考虑另一种设计期望,即我们希望最大化表示中包含的关于任务且不被敏感属性或秘密共享的信息 $I(Y;T|S)$,同时约束无关信息的量,即确保 $I(Y;X|T,S) \leq r$。在这两种情况下,我们都采用了 Functional Representation Lemma 和 Strong Functional Representation Lemma 的扩展版本,并研究了所得界限的紧致性。通过将敏感属性视为秘密,这里的每个结果也都可以被解释为具有完美隐私的编码问题。
英文摘要:
In this article, we study the fundamental limits in the design of fair and/or private representations achieving perfect demographic parity and/or perfect privacy through the lens of information theory. More precisely, given some useful data $X$ that we wish to employ to solve a task $T$, we consider the design of a representation $Y$ that has no information of some sensitive attribute or secret $S$, that is, such that $I(Y;S) = 0$. We consider two scenarios. First, we consider a design desiderata where we want to maximize the information $I(Y;T)$ that the representation contains about the task, while constraining the level of compression (or encoding rate), that is, ensuring that $I(Y;X) \leq r$. Second, inspired by the Conditional Fairness Bottleneck problem, we consider a design desiderata where we want to maximize the information $I(Y;T|S)$ that the representation contains about the task which is not shared by the sensitive attribute or secret, while constraining the amount of irrelevant information, that is, ensuring that $I(Y;X|T,S) \leq r$. In both cases, we employ extended versions of the Functional Representation Lemma and the Strong Functional Representation Lemma and study the tightness of the obtained bounds. Every result here can also be interpreted as a coding with perfect privacy problem by considering the sensitive attribute as a secret.
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。