Probabilistic Sufficient Explanations
Probabilistic Sufficient Explanations
复制标题
DOI：
10.24963/ijcai.2021/424
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Eric Wang;Pasha Khosravi;Guy Van den Broeck
中科院分区：
文献类型：
--
作者：
Eric Wang;Pasha Khosravi;Guy Van den Broeck
理解学习分类器的行为是一项重要的任务，已经提出了各种黑盒解释，逻辑推理方法和模型特定的方法。在本文中，我们引入概率充分解释，制定解释分类的实例选择“最简单的”子集的功能，只有观察这些功能是“足够的”来解释分类。也就是说，这足以为我们提供强概率保证，即当在数据分布下观察到所有特征时，模型将表现出相似的行为。此外，我们利用易处理的概率推理工具，如概率电路和预期的预测，设计一个可扩展的算法，找到所需的解释，同时保持保证完好无损。我们的实验表明，我们的算法在寻找足够的解释的有效性，并显示其优势相比，推理和逻辑解释。
Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed. In this paper, we introduce probabilistic sufficient explanations, which formulate explaining an instance of classification as choosing the "simplest" subset of features such that only observing those features is "sufficient" to explain the classification. That is, sufficient to give us strong probabilistic guarantees that the model will behave similarly when all features are observed under the data distribution. In addition, we leverage tractable probabilistic reasoning tools such as probabilistic circuits and expected predictions to design a scalable algorithm for finding the desired explanations while keeping the guarantees intact. Our experiments demonstrate the effectiveness of our algorithm in finding sufficient explanations, and showcase its advantages compared to Anchors and logical explanations.