A Multiobjective Genetic Algorithm to Evolving Local Interpretable Model-Agnostic Explanations for Deep Neural Networks in Image Classification

Bin Wang, Wenbin Pei, Bing Xue, Mengjie Zhang

Abstract: Deep convolutional neural networks have become a dominant solution for numerous image classification tasks. However, a main criticism is the poor explainability due to the black-box characteristic, which hurdles the extensive usage of deep convolutional neural networks. To address this issue, this article proposes a new evolutionary multiobjective-based method, which aims to explain the behaviors of deep convolutional neural networks by evolving local explanations on specific images. To the best of our knowledge, this is the first evolutionary multiobjective method to evolve local explanations. The proposed method is model agnostic, i.e., it is applicable to explain any deep convolutional neural networks. ImageNet is used to examine the effectiveness of the proposed method. Three well-known deep convolutional neural networks—VGGNet, ResNet, and MobileNet, are chosen to demonstrate the model-agnostic characteristic. Based on the experimental results, it can be observed that the local explanations are understandable to end users, who need to check the sensibility of the evolved explanations to decide whether to trust the predictions made by the deep convolutional neural networks. Furthermore, the local explanations evolved by the proposed method improves the confidence of deep convolutional neural networks making the predictions. Finally, the pareto front and convergence analyses indicate that the proposed method can form a good set of nondominated solutions.