As machine learning applications proliferate, we need an understanding of
their potential for harm. However, current fairness metrics are rarely grounded
in human psychological experiences of harm. Drawing on the social psychology of
stereotypes, we use a case study of gender stereotypes in image search to
examine how people react to machine learning errors. First, we use survey
studies to show that not all machine learning errors reflect stereotypes nor
are equally harmful. Then, in experimental studies we randomly expose
participants to stereotype-reinforcing, -violating, and -neutral machine
learning errors. We find stereotype-reinforcing errors induce more
experientially (i.e., subjectively) harmful experiences, while having minimal
changes to cognitive beliefs, attitudes, or behaviors. This experiential harm
impacts women more than men. However, certain stereotype-violating errors are
more experientially harmful for men, potentially due to perceived threats to
masculinity. We conclude that harm cannot be the sole guide in fairness
mitigation, and propose a nuanced perspective depending on who is experiencing
what harm and why.

通过社会心理学的视角，以性别刻板印象在图像搜索中的案例研究为例，本文研究了机器学习误差对人们心理体验的影响，发现刻板印象加强型误差会引起更多主观上的伤害体验，而对认知信念、态度或行为的影响较小，这种伤害对女性的影响较大。然而，某些违背刻板印象的误差对男性而言会造成更多主观伤害，可能是因为被认为威胁到男性气概。因此，本文得出结论，公平度量不能仅以伤害为唯一指南，应根据不同受伤者的感受和原因，提出更细致的观点。

测量机器学习偏见造成的伤害：需要了解哪种错误以什么方式伤害了谁

Measuring machine learning harms from stereotypes: requires  understanding who is being harmed by which errors in what ways

Deep learning is increasingly being used in high-stake decision making
applications that affect individual lives. However, deep learning models might
exhibit algorithmic discrimination behaviors with respect to protected groups,
potentially posing negative impacts on individuals and society. Therefore,
fairness in deep learning has attracted tremendous attention recently. We
provide a review covering recent progresses to tackle algorithmic fairness
problems of deep learning from the computational perspective. Specifically, we
show that interpretability can serve as a useful ingredient to diagnose the
reasons that lead to algorithmic discrimination. We also discuss fairness
mitigation approaches categorized according to three stages of deep learning
life-cycle, aiming to push forward the area of fairness in deep learning and
build genuinely fair and reliable deep learning systems.

该文章从计算视角对深度学习算法的公平性问题进行了综述和分类总结，重点讨论了通过解释性来诊断算法歧视和推进公平深度学习体系的公平化方法。