Idioma:

Towards Reliable Software Analytics: Systematic Integration of Explanations from Different Model-Agnostic Techniques

Lee, Gichan ; Lee, Scott Uk-Jin

IEEE software, 2023-02, p.1-8 [Periódico revisado por pares]

Texto completo disponível

Citações Citado por

Título:
Towards Reliable Software Analytics: Systematic Integration of Explanations from Different Model-Agnostic Techniques
Autor: Lee, Gichan ; Lee, Scott Uk-Jin
Assuntos: Analytical models ; Computational modeling ; Electric breakdown ; Predictive models ; Radio frequency ; Software ; Software engineering
É parte de: IEEE software, 2023-02, p.1-8
Descrição: Recently, software analytics began to explain the reasons behind the predictions of machine learning (ML) and artificial intelligence (AI) models for various aspects of software projects using model-agnostic techniques derived from explainable artificial intelligence (XAI) domain. However, there is no guarantee that different modelagnostic techniques generate consistent explanations for the same predictions. Therefore, practitioners may obtain different insights depending on the technique they use. This article discusses in detail the problems caused by the inconsistent explanations generated from different model-agnostic techniques. In addition, we propose a method to integrate inconsistent explanations to derive information which can provide more useful and reliable software analytics to practitioners. Lastly, we discuss the future research directions for which explainable artificial intelligence for software engineering (XAI4SE) community to carry forward in exploiting the practical value of model-agnostic techniques.
Editor: IEEE
Idioma: Inglês

Voltar para lista de resultados