Statistical Equity: A Fairness Classification Objective
This work addresses fairness in machine learning, which is a critical issue for society, but it appears incremental as it builds on existing fairness definitions.
The authors tackled the problem of fairness in machine learning by proposing a new fairness definition based on equity that accounts for historical biases in data, and they demonstrated its effectiveness through automatic and human evaluations.
Machine learning systems have been shown to propagate the societal errors of the past. In light of this, a wealth of research focuses on designing solutions that are "fair." Even with this abundance of work, there is no singular definition of fairness, mainly because fairness is subjective and context dependent. We propose a new fairness definition, motivated by the principle of equity, that considers existing biases in the data and attempts to make equitable decisions that account for these previous historical biases. We formalize our definition of fairness, and motivate it with its appropriate contexts. Next, we operationalize it for equitable classification. We perform multiple automatic and human evaluations to show the effectiveness of our definition and demonstrate its utility for aspects of fairness, such as the feedback loop.