arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.10216cs.LGcs.GT
收藏

对所有人公平:分类的最佳公平保证

Fair for All: Best-effort Fairness Guarantees for Classification

Duke University(杜克大学);Tsinghua University(清华大学);University of Illinois at Chicago(芝加哥大学伊利诺伊分校)

Anilesh K. Krishnaswamy, Zhihao Jiang, Kangning Wang, Yu Cheng, Kamesh Munagala

摘要:

基于群体的公平性概念的标准方法,如\emph{parity}和\emph{equalized odds},试图在已知群体(基于种族,性别等)之间平衡绝对的绩效测量。因此,一个本来就很难分类的群体可能会阻碍其他群体的业绩;而且无法为不可预见的群体提供任何保证。相反,我们提出了一个公平的概念,其保证,在每个组$g$类$\mathcal{G}$,是相对于性能最好的分类器$g$。我们将这一概念应用于广泛的组类,特别是,其中(a)$\mathcal{G}$由数据中所有可能的组(子集)组成,以及(b)$\mathcal{G}$更精简。对于第一个设置,这是类似于组是完全未知的,我们设计的{ \sc PF}(比例公平)分类器,它保证,在任何可能的组$g$,准确性是成比例的最佳分类器的$g$,缩放的相对大小$g$在数据集中。由于包含了所有可能的组,其中一些可能太复杂而不相关,因此对于较小的子集,最坏情况的理论保证必须按比例较弱。对于第二种设置,我们设计了{ \sc BeFair}(尽力公平)框架,该框架在每个$g \in \mathcal{G}$上寻求准确性,该准确性近似于$g$上的最佳分类器的准确性,而与$g$的大小无关。针对这样的保证结果在一个非凸的问题,我们设计了新的技术来绕过这个困难时,$\mathcal{G}$是一组线性假设。我们在真实世界的数据集上测试我们的算法,并对其性能提出有趣的比较见解。

英文摘要:

Standard approaches to group-based notions of fairness, such as \emph{parity} and \emph{equalized odds}, try to equalize absolute measures of performance across known groups (based on race, gender, etc.). Consequently, a group that is inherently harder to classify may hold back the performance on other groups; and no guarantees can be provided for unforeseen groups. Instead, we propose a fairness notion whose guarantee, on each group $g$ in a class $\mathcal{G}$, is relative to the performance of the best classifier on $g$. We apply this notion to broad classes of groups, in particular, where (a) $\mathcal{G}$ consists of all possible groups (subsets) in the data, and (b) $\mathcal{G}$ is more streamlined. For the first setting, which is akin to groups being completely unknown, we devise the {\sc PF} (Proportional Fairness) classifier, which guarantees, on any possible group $g$, an accuracy that is proportional to that of the optimal classifier for $g$, scaled by the relative size of $g$ in the data set. Due to including all possible groups, some of which could be too complex to be relevant, the worst-case theoretical guarantees here have to be proportionally weaker for smaller subsets. For the second setting, we devise the {\sc BeFair} (Best-effort Fair) framework which seeks an accuracy, on every $g \in \mathcal{G}$, which approximates that of the optimal classifier on $g$, independent of the size of $g$. Aiming for such a guarantee results in a non-convex problem, and we design novel techniques to get around this difficulty when $\mathcal{G}$ is the set of linear hypotheses. We test our algorithms on real-world data sets, and present interesting comparative insights on their performance.

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。

↑