论文标题
机器学习决策的消费者驱动解释：鲁棒性的实证研究
Consumer-Driven Explanations for Machine Learning Decisions: An Empirical Study of Robustness
论文作者
论文摘要
对于非技术消费者来说，许多用于解释机器学习预测的方法实际上是具有挑战性的。本文建立在一种称为TED的替代消费者驱动方法的基础上，该方法要求在培训数据中提供解释以及目标标签。使用信贷批准和员工保留申请的半合成数据，进行了实验，以调查具有TED的一些实际考虑因素，包括其具有不同分类算法的性能，不同的解释和解释的可变性。提出了一种新算法来处理一些培训示例没有解释的情况。我们的结果表明，TED对越来越多的解释，嘈杂的解释和大量缺失解释的部分是强大的，从而促进了其实际部署。
Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data from credit approval and employee retention applications, experiments are conducted to investigate some practical considerations with TED, including its performance with different classification algorithms, varying numbers of explanations, and variability in explanations. A new algorithm is proposed to handle the case where some training examples do not have explanations. Our results show that TED is robust to increasing numbers of explanations, noisy explanations, and large fractions of missing explanations, thus making advances toward its practical deployment.
