论文标题
机器公平的不可能定理 - 因果观点
The Impossibility Theorem of Machine Fairness -- A Causal Perspective
论文作者
论文摘要
随着在社会和经济环境中对机器学习的普遍使用，人们对AI社区的机器偏见概念引起了兴趣。经过历史数据培训的模型反映了社会中存在的偏见，并通过他们的决策传播到未来。社区中使用了三个重要的机器公平指标，并且从统计上证明，不可能同时满足它们。这导致了关于公平定义的歧义。在本报告中，介绍了公平定理的因果观点，以及机器公平的因果目标。
With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility theorem of fairness is presented along with a causal goal for machine fairness.
