Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation
Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation
复制标题
DOI：
10.1609/aaai.v36i9.21195
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Thien Q. Tran;Kazuto Fukuchi;Youhei Akimoto;Jun Sakuma
中科院分区：
文献类型：
--
作者：
Thien Q. Tran;Kazuto Fukuchi;Youhei Akimoto;Jun Sakuma
我们的目标是解释一个黑盒分类器的形式：“数据X被分类为类Y，因为X有A，B和没有C”，其中A，B和C是高级概念。挑战在于，我们必须以无监督的方式发现一组概念，即，A，B和C，这对解释分类器很有用。我们首先介绍了一个结构生成模型，适合表达和发现这样的概念。然后，我们提出了一个学习过程，同时学习的数据分布，并鼓励某些概念有一个很大的因果关系的分类器输出的影响。我们的方法还允许用户的先验知识，以诱导高的概念的可解释性容易集成。最后，使用多个数据集，我们证明了所提出的方法可以发现有用的概念，以这种形式进行解释。
We aim to explain a black-box classifier with the form: "data X is classified as class Y because X has A, B and does not have C" in which A, B, and C are high-level concepts. The challenge is that we have to discover in an unsupervised manner a set of concepts, i.e., A, B and C, that is useful for explaining the classifier. We first introduce a structural generative model that is suitable to express and discover such concepts. We then propose a learning process that simultaneously learns the data distribution and encourages certain concepts to have a large causal influence on the classifier output. Our method also allows easy integration of user's prior knowledge to induce high interpretability of concepts. Finally, using multiple datasets, we demonstrate that the proposed method can discover useful concepts for explanation in this form.