论文标题
准确的公平性：改善个人公平而不交易准确性
Accurate Fairness: Improving Individual Fairness without Trading Accuracy
论文作者
论文摘要
准确性和个人公平性对于值得信赖的机器学习至关重要，但是这两个方面通常彼此不兼容，因此增强一个方面可能不可避免地会因真正的偏见或虚假公平而不可避免地牺牲另一方面。我们在本文中提出了一个新的公平标准，准确的公平性，以使个人公平与准确性保持一致。非正式地，它要求个人和个人类似的对应物的治疗以符合统一的目标，即个人的基础真理。我们证明，准确的公平性也意味着与类似子人群的结合的典型群体公平标准。然后，我们提出了一种暹罗公平性进行处理的方法，以最大程度地减少在准确的公平限制下机器学习模型的准确性和公平性损失。据我们所知，这是第一次将暹罗方法改编成偏见。我们还提出了公平性混乱的基于矩阵的指标，公平精神，公平录音和公平-F1分数，以量化准确性和个人公平性之间的权衡。与流行公平数据集的比较案例研究表明，我们的暹罗公平方法平均可以达到1.02％-8.78％的个人公平性（就通过意识而言公平性而言）和8.38％-13.69％的准确性，而准确性为10.09％-20.57％，而真实的公平率则提高5.43％-10.0.01％的公平率，并比率更高。这表明我们的暹罗公平方法确实可以改善个人公平，而无需交易准确性。最后，采用准确的公平标准和暹罗公平方法来通过真正的CTRIP数据集来减轻可能的服务歧视，平均公平服务的客户（具体来说，以公平方式超过81.29％的客户）比基线模型多了81.29％）。
Accuracy and individual fairness are both crucial for trustworthy machine learning, but these two aspects are often incompatible with each other so that enhancing one aspect may sacrifice the other inevitably with side effects of true bias or false fairness. We propose in this paper a new fairness criterion, accurate fairness, to align individual fairness with accuracy. Informally, it requires the treatments of an individual and the individual's similar counterparts to conform to a uniform target, i.e., the ground truth of the individual. We prove that accurate fairness also implies typical group fairness criteria over a union of similar sub-populations. We then present a Siamese fairness in-processing approach to minimize the accuracy and fairness losses of a machine learning model under the accurate fairness constraints. To the best of our knowledge, this is the first time that a Siamese approach is adapted for bias mitigation. We also propose fairness confusion matrix-based metrics, fair-precision, fair-recall, and fair-F1 score, to quantify a trade-off between accuracy and individual fairness. Comparative case studies with popular fairness datasets show that our Siamese fairness approach can achieve on average 1.02%-8.78% higher individual fairness (in terms of fairness through awareness) and 8.38%-13.69% higher accuracy, as well as 10.09%-20.57% higher true fair rate, and 5.43%-10.01% higher fair-F1 score, than the state-of-the-art bias mitigation techniques. This demonstrates that our Siamese fairness approach can indeed improve individual fairness without trading accuracy. Finally, the accurate fairness criterion and Siamese fairness approach are applied to mitigate the possible service discrimination with a real Ctrip dataset, by on average fairly serving 112.33% more customers (specifically, 81.29% more customers in an accurately fair way) than baseline models.
