When neural networks are employed for high-stakes decision making, it is desirable for the neural networks to provide explanation for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is important to flag potential outliers for in-depth verification by domain experts. In this work we propose to unify two differing aspects of explainability with outlier detection. We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for its prediction and at the same time identify regions of similarity between the predicted sample and the examples. The examples are real prototypical cases sampled from the training set via our novel iterative prototype replacement algorithm. Furthermore, we propose to use the prototype similarity scores for identifying outliers. We compare performances in terms of classification, explanation quality, and outlier detection of our proposed network with other baselines. We show that our prototype-based networks beyond similarity kernels deliver meaningful explanation and promising outlier detection results without compromising classification accuracy.
翻译:当神经网络被用于作出高度决策时,神经网络最好能对其预测作出解释,以便我们了解促成决定的特征。与此同时,必须标出潜在的异常点,供域专家进行深入核查。在这项工作中,我们提议将解释性和异度检测两个不同的方面统一起来。我们主张更广泛地采用基于原型的学生网络,以便能够为预测提供以实例为基础的解释,同时查明预测样本和实例之间的相似区域。这些实例是从我们新颖的迭代原型替代算法中培训中抽样的真正的原型案例。此外,我们提议使用原型相似性分数来识别外部点。我们将我们拟议网络的分类、解释质量和异度检测与其他基线进行对比。我们指出,我们的原型网络在类似性内核之外可以提供有意义的解释,并有望在不损害分类准确性的前提下获得外部检测结果。