Shapley Explanation Networks
Shapley Explanation Networks
复制标题
DOI：
--
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Rui Wang;Xiaoqian Wang;David I. Inouye
中科院分区：
文献类型：
--
作者：
Rui Wang;Xiaoqian Wang;David I. Inouye
Shapley值已成为最流行的特征属性解释方法之一。然而，大多数先前的工作都集中在事后Shapley解释上，由于其指数时间复杂度，计算要求很高，并且在训练过程中排除了基于Shapley解释的模型正则化。因此，我们建议将Shapley值本身作为深层模型中的潜在表示，从而使Shapley解释成为建模范式中的一等公民。这种内在解释方法可以实现分层解释，在训练期间对模型进行解释正则化，并在测试时进行快速解释计算。我们定义了Shapley变换，它将输入转换为给定特定函数的Shapley表示。我们将Shapley变换操作为神经网络模块，并通过组成Shapley模块来构建浅层和深层网络，称为ShapNets。我们证明了我们的Shallow ShapNets计算精确的Shapley值，而我们的Deep ShapNets保持了Shapley值的缺失和准确性。我们在合成和真实世界的数据集上证明，我们的ShapNet能够实现分层Shapley解释，训练期间的新颖Shapley正则化，以及快速计算，同时保持合理的性能。代码可在https://github.com/inouye-lab/ShapleyExplanationNetworks上获得。
Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on post-hoc Shapley explanations, which can be computationally demanding due to its exponential time complexity and preclude model regularization based on Shapley explanations during training. Thus, we propose to incorporate Shapley values themselves as latent representations in deep models thereby making Shapley explanations first-class citizens in the modeling paradigm. This intrinsic explanation approach enables layer-wise explanations, explanation regularization of the model during training, and fast explanation computation at test time. We define the Shapley transform that transforms the input into a Shapley representation given a specific function. We operationalize the Shapley transform as a neural network module and construct both shallow and deep networks, called ShapNets, by composing Shapley modules. We prove that our Shallow ShapNets compute the exact Shapley values and our Deep ShapNets maintain the missingness and accuracy properties of Shapley values. We demonstrate on synthetic and real-world datasets that our ShapNets enable layer-wise Shapley explanations, novel Shapley regularizations during training, and fast computation while maintaining reasonable performance. Code is available at https://github.com/inouye-lab/ShapleyExplanationNetworks.