Enhancing Feature Selection and Interpretability in AI Regression Tasks Through Feature Attribution
This work addresses the need for better feature selection and interpretability in regression problems, particularly in industrial applications like turbo machinery, but it is incremental as it adapts existing XAI methods to a new domain.
The study tackled the problem of improving accuracy and stability in AI regression tasks by using feature attribution methods to filter uninformative features, applied to blade vibration analysis in turbo machinery development.
Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant applications. However, relatively little attention has been given to using these methods to improve the performance and robustness of deep learning algorithms. Additionally, much of the existing XAI work primarily addresses classification problems. In this study, we investigate the potential of feature attribution methods to filter out uninformative features in input data for regression problems, thereby improving the accuracy and stability of predictions. We introduce a feature selection pipeline that combines Integrated Gradients with k-means clustering to select an optimal set of variables from the initial data space. To validate the effectiveness of this approach, we apply it to a real-world industrial problem - blade vibration analysis in the development process of turbo machinery.