Machine learning models, in particular artificial neural networks, are increasingly used to inform decision making in high-stakes scenarios across a variety of fields--from financial services, to public safety, and healthcare. While neural networks have achieved remarkable performance in many settings, their complex nature raises concerns on their reliability, trustworthiness, and fairness in real-world scenarios. As a result, several a-posteriori explanation methods have been proposed to highlight the features that influence a model's prediction. Notably, the Shapley value--a game theoretic quantity that satisfies several desirable properties--has gained popularity in the machine learning explainability literature. More traditionally, however, feature importance in statistical learning has been formalized by conditional independence, and a standard way to test for it is via Conditional Randomization Tests (CRTs). So far, these two perspectives on interpretability and feature importance have been considered distinct and separate. In this work, we show that Shapley-based explanation methods and conditional independence testing for feature importance are closely related. More precisely, we prove that evaluating a Shapley coefficient amounts to performing a specific set of conditional independence tests, as implemented by a procedure similar to the CRT but for a different null hypothesis. Furthermore, the obtained game-theoretic values upper bound the $p$-values of such tests. As a result, we grant large Shapley coefficients with a precise statistical sense of importance with controlled type I error.
翻译:机器学习模型,特别是人工神经网络,越来越多地被用来为从金融服务到公共安全和医疗保健等各个领域的高风险情景中的决策提供信息。虽然神经网络在许多环境中取得了显著的性能,但其复杂的性质引起了人们对其可靠性、可信赖性和真实世界情景中公平性的关切。因此,提出了几种不同角度的解释方法,以突出影响模型预测的特征。值得注意的是,Shapley 价值-a游戏理论性数量在机器学习解释性文献中达到了一些可取的属性,在机器学习可解释性文献中越来越受欢迎。然而,传统上,在统计学习中,由于有条件独立而正式确立其重要性,而测试标准方法则是通过有条件随机随机化测试(CRTs)测试测试来测试其可靠性、可信度和公平性。迄今为止,关于可解释性和特征重要性的这两种观点被认为是截然不同的。在这项工作中,我们表明,基于简单解释性解释的方法和对特征重要性的有条件独立测试是密切相关的。更确切的,我们证明,评估一个精度系数相当于具体设定美元的统计价值的固定值标准,通过一种不同的程序进行固定的C值测试。