LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
arXiv:2005.01427 · doi:10.3390/electronics14050929
Abstract
Explainable artificial intelligence provides tools to better understand predictive models and their decisions, but many such methods are limited to producing insights with respect to a single class. When generating explanations for several classes, reasoning over them to obtain a comprehensive view may be difficult since they can present competing or contradictory evidence. To address this challenge we introduce the novel paradigm of multi-class explanations. We outline the theory behind such techniques and propose a local surrogate model based on multi-output regression trees -- called LIMEtree -- that offers faithful and consistent explanations of multiple classes for individual predictions while being post-hoc, model-agnostic and data-universal. On top of strong fidelity guarantees, our implementation delivers a range of diverse explanation types, including counterfactual statements favoured in the literature. We evaluate our algorithm with respect to explainability desiderata, through quantitative experiments and via a pilot user study, on image and tabular data classification tasks, comparing it to LIME, which is a state-of-the-art surrogate explainer. Our contributions demonstrate the benefits of multi-class explanations and wide-ranging advantages of our method across a diverse set of scenarios.
References in corpus (15)
- Scikit-learn: Machine Learning in Python
- Explaining Explanations in AI
- Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
- FACE: Feasible and Actionable Counterfactual Explanations
- Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
- One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency
- Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
- Explaining the Explainer: A First Theoretical Analysis of LIME
- Defining Locality for Surrogates in Post-hoc Interpretablity
- FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems
- Interpretable Representations in Explainable AI: From Theory to Practice
- What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks
- Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations
- Helpful, Misleading or Confusing: How Humans Perceive Fundamental Building Blocks of Artificial Intelligence Explanations
- (Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibility