期刊
AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY
卷 -, 期 -, 页码 491-501出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3461702.3462558
关键词
Clustering; Fairness; Interpretability; Maximum-likelihood estimation
Fair clustering is the process of grouping similar entities together while satisfying a mathematically defined fairness metric. The study focuses on identifying the fairness constraint from limited demonstrations by experts and presents algorithms to generate fair and interpretable clusters. The approach is also extended to novel fairness metrics and investigates how to produce interpretable solutions.
Fair clustering is the process of grouping similar entities together, while satisfying a mathematically well-defined fairness metric as a constraint. Due to the practical challenges in precise model specification, the prescribed fairness constraints are often incomplete and act as proxies to the intended fairness requirement. Clustering with proxies may lead to biased outcomes when the system is deployed. We examine how to identify the intended fairness constraint for a problem based on limited demonstrations from an expert. Each demonstration is a clustering over a subset of the data. We present an algorithm to identify the fairness metric from demonstrations and generate clusters using existing off-the-shelf clustering techniques, and analyze its theoretical properties. To extend our approach to novel fairness metrics for which clustering algorithms do not currently exist, we present a greedy method for clustering. Additionally, we investigate how to generate interpretable solutions using our approach. Empirical evaluation on three real-world datasets demonstrates the effectiveness of our approach in quickly identifying the underlying fairness and interpretability constraints, which are then used to generate fair and interpretable clusters.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据