A Multiobjective Genetic Algorithm to Evolving Local Interpretable Model-Agnostic Explanations for Deep Neural Networks in Image Classification
- 30 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 28 (4) , 903-917
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 paper proposes a new evolutionary multi-objective based method, which aims to explain the behaviours of deep convolutional neural networks by evolving local explanations on specific images. To the best of our knowledge, this is the first evolutionary multi-objective 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 modelagnostic 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. Lastly, the pareto front and convergence analyses indicate that the proposed method can form a good set of nondominated solutions.Keywords
Funding Information
- Marsden Fund of New Zealand Government (VUW1913, VUW1914)
- Science for Technological Innovation Challenge (SfTI) Fund (E3603/2903)
- University Research Fund at Victoria University of Wellington (223805/3986)
- Ministry of Business, Innovation and Employment (MBIE) Data Science Strategic Science Investment Fund (RTVU1914)
- National Natural Science Foundation of China (61876169)
- Huayin Medical (E3791/4165)
- MBIE Endeavor Research Programme (C11X2001)
This publication has 45 references indexed in Scilit:
- Particle Swarm optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks2020
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks2019
- Evolving Deep Neural Networks2019
- An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasetsNature Biomedical Engineering, 2018
- A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification2018
- Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification2018
- Deep Residual Learning for Image Recognition2016
- Learning Deep Features for Discriminative Localization2016
- A peek into the black box: exploring classifiers by randomizationData Mining and Knowledge Discovery, 2014