Applying Genetic Programming to Improve Interpretability in Machine Learning Models
This addresses the need for better interpretability in AI systems, particularly for users dealing with complex models, though it is an incremental improvement by applying genetic programming to an existing bottleneck.
The paper tackled the problem of explaining decisions from black-box AI models by proposing Genetic Programming Explainer (GPX), which generates local symbolic expressions for interpretability, and demonstrated that GPX produces more accurate understanding than state-of-the-art methods across three model types and twenty datasets.
Explainable Artificial Intelligence (or xAI) has become an important research topic in the fields of Machine Learning and Deep Learning. In this paper, we propose a Genetic Programming (GP) based approach, named Genetic Programming Explainer (GPX), to the problem of explaining decisions computed by AI systems. The method generates a noise set located in the neighborhood of the point of interest, whose prediction should be explained, and fits a local explanation model for the analyzed sample. The tree structure generated by GPX provides a comprehensible analytical, possibly non-linear, symbolic expression which reflects the local behavior of the complex model. We considered three machine learning techniques that can be recognized as complex black-box models: Random Forest, Deep Neural Network and Support Vector Machine in twenty data sets for regression and classifications problems. Our results indicate that the GPX is able to produce more accurate understanding of complex models than the state of the art. The results validate the proposed approach as a novel way to deploy GP to improve interpretability.