Explainable Artificial Intelligence by Genetic Programming: A Survey

Explainable artificial intelligence (XAI) has received great interest in the recent decade, due to its importance in critical application domains, such as self-driving cars, law, and healthcare. Genetic programming (GP) is a powerful evolutionary algorithm for machine learning. Compared with other standard machine learning models such as neural networks, the models evolved by GP tend to be more interpretable due to their model structure with symbolic components. However, interpretability has not been explicitly considered in GP until recently, following the surge in the popularity of XAI. This article provides a comprehensive review of the studies on GP that can potentially improve the model interpretability, both explicitly and implicitly, as a byproduct. We group the existing studies related to explainable artificial intelligence by GP into two categories. The first category considers the intrinsic interpretability, aiming to directly evolve more interpretable (and effective) models by GP. The second category focuses on post-hoc interpretability, which uses GP to explain other black-box machine learning models, or explain the models evolved by GP by simpler models such as linear models. This comprehensive survey demonstrates the strong potential of GP for improving the interpretability of machine learning models and balancing the complex tradeoff between model accuracy and interpretability.

Automated summary

Explainable artificial intelligence (XAI) has gained significant attention, particularly in critical domains like self-driving cars, law, and healthcare. Genetic programming (GP), an evolutionary algorithm for machine learning, has been shown to produce more interpretable models compared to neural networks. This article comprehensively reviews studies on how GP can improve model interpretability, either by directly evolving interpretable models or by explaining opaque models using GP or simpler models. The survey highlights the potential of GP in addressing the tradeoff between model accuracy and interpretability.