Adaptive Data Debiasing through Bounded Exploration
This addresses fairness and accuracy issues in algorithmic decisions for affected groups, but it is incremental as it builds on existing debiasing methods with adaptive exploration.
The authors tackled the problem of biases in training datasets for algorithmic decision-making by proposing an adaptive exploration algorithm that selectively deviates from loss-minimizing rules to reduce statistical biases, showing through experiments on synthetic and real-world datasets that it can debias data effectively.
Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets through adaptive and bounded exploration in a classification problem with costly and censored feedback. Exploration in this context means that at times, and to a judiciously-chosen extent, the decision maker deviates from its (current) loss-minimizing rule, and instead accepts some individuals that would otherwise be rejected, so as to reduce statistical data biases. Our proposed algorithm includes parameters that can be used to balance between the ultimate goal of removing data biases -- which will in turn lead to more accurate and fair decisions, and the exploration risks incurred to achieve this goal. We analytically show that such exploration can help debias data in certain distributions. We further investigate how fairness criteria can work in conjunction with our data debiasing algorithm. We illustrate the performance of our algorithm using experiments on synthetic and real-world datasets.