Can Genetic Programming Perform Explainable Machine Learning for Bioinformatics?

Hu, Ting

doi:10.1007/978-3-030-39958-0_4

Cited by 8 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach is to consider the fitness values of the GP models that features appeared [167], where the results show how different numbers of top ranked features affect the classification performance, which can help understand and explain the data and the generated GP model. Hu [168] developed a linear GP method, where the final model was learned by using the most frequently occurred features from the a previous one as input, i.e., using a significantly reduced feature set to build the model. The results showed that the selected features can help linear GP obtain significantly better prediction performance and more interpretable models.…”

Section: Fewer Distinct Features In Gp Modelsmentioning

confidence: 99%

Explainable Artificial Intelligence by Genetic Programming: A Survey

Mei

Chen

Lensen

et al. 2023

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

Explainable artificial intelligence 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 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 genetic programming until recently, following the surge in popularity of explainable artificial intelligence. This paper provides a comprehensive review of the studies on genetic programming 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 genetic programming into two categories. The first category considers the intrinsic interpretability, aiming to directly evolve more interpretable (and effective) models by genetic programming. The second category focuses on posthoc interpretability, which uses genetic programming to explain other black-box machine learning models, or explain the models evolved by genetic programming by simpler models such as linear models. This comprehensive survey demonstrates the strong potential of genetic programming for improving the interpretability of machine learning models and balancing the complex trade-off between model accuracy and interpretability.

show abstract

Section: Fewer Distinct Features In Gp Modelsmentioning

confidence: 99%

Explainable Artificial Intelligence by Genetic Programming: A Survey

Mei

Chen

Lensen

et al. 2023

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

show abstract

“…Genetic algorithms are a straightforward and effective approach to feature selection, with a natural representation in the form of strings of 1s and 0s, making them a popular choice for feature selection [44,49,59]. Genetic programming can also be used for feature selection since the inclusion of features in a tree or linear genetic program is intrinsically evolved with the program [19,20,48]. For an in-depth review of genetic programming methods, we refer the reader to [58].…”

Section: Feature Selection and Feature Engineeringmentioning

confidence: 99%

Genetic Programming for Interpretable and Explainable Machine Learning

2023

Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Machine learning models are increasingly being used in critical sectors, but their black-box nature has raised concerns about accountability and trust. The field of explainable artificial intelligence (XAI) or explainable machine learning (XML) has emerged in response to the need for human understanding of these models. Evolutionary computing, as a family of powerful optimization and learning tools, has significant potential to contribute to XAI/XML. In this chapter, we provide a brief introduction to XAI/XML and review various techniques in current use for explaining machine learning models. We then focus on how evolutionary computing can be used in XAI/XML, and review some approaches which incorporate EC techniques. We also discuss some open challenges in XAI/XML and opportunities for future research in this field using EC. Our aim is to demonstrate that evolutionary computing is well-suited for addressing current problems in explainability, and to encourage further exploration of these methods to contribute to the development of more transparent, trustworthy and accountable machine learning models.

show abstract

“…It has been used to automate machine learning pipelines (Olson and Moore 2016). Moreover, it has also been employed to generate explanations for machine learning models (Cavaliere et al 2020;Hu 2020). One can pose a simple question at this point: how explainable are GP-generated models themselves?…”

Section: Introductionmentioning

confidence: 99%

Simplification of genetic programs: a literature survey

Javed

Gobet

Lane

2022

Data Min Knowl Disc

View full text Add to dashboard Cite

Genetic programming (GP), a widely used evolutionary computing technique, suffers from bloat—the problem of excessive growth in individuals’ sizes. As a result, its ability to efficiently explore complex search spaces reduces. The resulting solutions are less robust and generalisable. Moreover, it is difficult to understand and explain models which contain bloat. This phenomenon is well researched, primarily from the angle of controlling bloat: instead, our focus in this paper is to review the literature from an explainability point of view, by looking at how simplification can make GP models more explainable by reducing their sizes. Simplification is a code editing technique whose primary purpose is to make GP models more explainable. However, it can offer bloat control as an additional benefit when implemented and applied with caution. Researchers have proposed several simplification techniques and adopted various strategies to implement them. We organise the literature along multiple axes to identify the relative strengths and weaknesses of simplification techniques and to identify emerging trends and areas for future exploration. We highlight design and integration challenges and propose several avenues for research. One of them is to consider simplification as a standalone operator, rather than an extension of the standard crossover or mutation operators. Its role is then more clearly complementary to other GP operators, and it can be integrated as an optional feature into an existing GP setup. Another proposed avenue is to explore the lack of utilisation of complexity measures in simplification. So far, size is the most discussed measure, with only two pieces of prior work pointing out the benefits of using time as a measure when controlling bloat.

show abstract

Can Genetic Programming Perform Explainable Machine Learning for Bioinformatics?

Cited by 8 publications

References 26 publications

Explainable Artificial Intelligence by Genetic Programming: A Survey

Explainable Artificial Intelligence by Genetic Programming: A Survey

Genetic Programming for Interpretable and Explainable Machine Learning

Simplification of genetic programs: a literature survey

Contact Info

Product

Resources

About