S-LIME: Stabilized-LIME for Model Explanation

Abstract

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the method itself and harming user trust. In this paper, we propose S-LIME, which utilizes a hypothesis testing framework based on central limit theorem for determining the number of perturbation points needed to guarantee stability of the resulting explanation. Experiments on both simulated and real world data sets are provided to demonstrate the effectiveness of our method.

arXiv commentIn Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '21), August 14--18, 2021, Virtual Event, Singapore

References in corpus (11)

• Least Angle Regression
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Discussion of "Least angle regression" by Efron et al
• Rejoinder to "Least angle regression" by Efron et al
• Scalable and accurate deep learning for electronic health records

Cited by in corpus (8)

• Adversarial attacks and defenses in explainable artificial intelligence: A survey
• Interpretability in Symbolic Regression: a benchmark of Explanatory Methods using the Feynman data set
• Calibrated Explanations: with Uncertainty Information and Counterfactuals
• Towards consistency of rule-based explainer and black box model -- fusion of rule induction and XAI-based feature importance
• Interpretable Machine Learning for Survival Analysis
• ControlBurn: Feature Selection by Sparse Forests
• A Model of Causal Explanation on Neural Networks for Tabular Data
• Unsupervised discovery of Interpretable Visual Concepts