论文标题
迈向个人公平的衡量深度学习
Towards a Measure of Individual Fairness for Deep Learning
论文作者
论文摘要
深度学习在人工智能方面取得了巨大进步，但是受过训练的神经网络通常反映和放大培训数据中的偏见，从而产生不公平的预测。我们提出了一种新颖的个人公平度量，称为预测灵敏度，该量度近似于特定预测取决于受保护的属性的程度。我们展示了如何使用现代深度学习框架中存在的标准自动分化能力来计算预测敏感性，并提出了初步的经验结果，这表明预测敏感性可能有效地衡量单个预测中的偏见。
Deep learning has produced big advances in artificial intelligence, but trained neural networks often reflect and amplify bias in their training data, and thus produce unfair predictions. We propose a novel measure of individual fairness, called prediction sensitivity, that approximates the extent to which a particular prediction is dependent on a protected attribute. We show how to compute prediction sensitivity using standard automatic differentiation capabilities present in modern deep learning frameworks, and present preliminary empirical results suggesting that prediction sensitivity may be effective for measuring bias in individual predictions.
