Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties—most frequently, that particular features are important or unimportant. These attribution priors are often based on attribution methods that are not guaranteed to satisfy desirable interpretability axioms, such as completeness and implementation invariance. Here we introduce attribution priors to optimize for higher-level properties of explanations, such as smoothness and sparsity, enabled by a fast new attribution method formulation called expected gradients that satisfies many important interpretability axioms. This improves model performance on many real-world tasks where previous attribution priors fail. Our experiments show that the gains from combining higher-level attribution priors with expected gradients attributions are consistent across image, gene expression and healthcare datasets. We believe that this work motivates and provides the necessary tools to support the widespread adoption of axiomatic attribution priors in many areas of applied machine learning. The implementations and our results have been made freely available to academic communities.

最近的研究表明，深度网络的特征归因方法本身可以纳入训练；这些归因先验优化了一个模型，该模型的归因具有某些理想的属性——最常见的是，特定特征是重要的还是不重要的。这些归因先验通常基于不能保证满足期望的可解释性公理的归因方法，例如完整性和实现不变性。在这里，我们引入了归因先验，以优化解释的更高级别属性，例如平滑度和稀疏性，这是通过一种称为预期梯度的快速新归因方法公式实现的，该公式满足许多重要的可解释性公理。这提高了模型在许多先前归因先验失败的实际任务上的性能。我们的实验表明，将高级归因先验与预期梯度归因相结合的收益在图像、基因表达和医疗保健数据集上是一致的。我们相信，这项工作激发并提供了必要的工具，以支持在应用机器学习的许多领域广泛采用公理归因先验。这些实现和我们的结果已免费提供给学术界。