异常检测中不公平性的基础——面部图像数据案例研究
Foundations for Unfairness in Anomaly Detection -- Case Studies in Facial Imaging Data
AI总结：
本研究探讨了深度异常检测在面部图像数据中的不公平性，通过实验分析基于自编码器和单类的算法，验证了代表性不足、虚假特征和标签噪声等不公平性来源及其层级关系。
摘要：
深度异常检测（AD）可以说是最具争议的数据分析任务之一，因为它所识别出的实体会被专门作为进一步调查或排除的目标。将人工智能应用于面部图像数据同样备受争议。本研究探讨了这两个领域的交叉点，以理解两个核心问题：这些算法对“谁”不公平，以及同样重要的“为什么”不公平。近期研究表明，深度异常检测可能对不同群体不公平，尽管它是无监督的；一项近期研究显示，在人物肖像中：有色人种男性被判定为离群点的可能性要高得多。我们研究了两大类异常检测算法：基于自编码器和基于单类的方法，它们有效地尝试压缩所有实例，而那些无法被轻易压缩的实例则被视为离群点。我们通过实验验证了不公平性的来源，例如某个群体的代表性不足（如有色人种相对罕见）、虚假的群体特征（如男性经常戴着帽子被拍照）以及群体标签噪声（如种族是主观的）。我们推测缺乏可压缩性是主要基础，其他因素由其引起，但实验结果却显示并非如此，并且我们展示了它们之间的自然层级关系。
英文摘要：
Deep anomaly detection (AD) is perhaps the most controversial of data analytic tasks as it identifies entities that are then specifically targeted for further investigation or exclusion. Also controversial is the application of AI to facial imaging data. This work explores the intersection of these two areas to understand two core questions: "Who" these algorithms are being unfair to and equally important "Why". Recent work has shown that deep AD can be unfair to different groups despite being unsupervised with a recent study showing that for portraits of people: men of color are far more likely to be chosen to be outliers. We study the two main categories of AD algorithms: autoencoder-based and single-class-based which effectively try to compress all the instances with those that can not be easily compressed being deemed to be outliers. We experimentally verify sources of unfairness such as the under-representation of a group (e.g. people of color are relatively rare), spurious group features (e.g. men are often photographed with hats), and group labeling noise (e.g. race is subjective). We conjecture that lack of compressibility is the main foundation and the others cause it but experimental results show otherwise and we present a natural hierarchy amongst them.
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。
