Local Universal Explainer (LUX) -- a rule-based explainer with factual, counterfactual and visual explanations
This addresses the problem of obtaining comprehensive explanations in AI for users needing interpretability, though it appears incremental as it builds on existing rule-based and SHAP methods.
The authors tackled the fragmentation in explainable AI by introducing Local Universal Explainer (LUX), a rule-based method that generates factual, counterfactual, and visual explanations, and it outperformed state-of-the-art approaches like LORE, EXPLAN, and Anchor in simplicity, fidelity, representativeness, and consistency.
Explainable artificial intelligence (XAI) is one of the most intensively developed area of AI in recent years. It is also one of the most fragmented with multiple methods that focus on different aspects of explanations. This makes difficult to obtain the full spectrum of explanation at once in a compact and consistent way. To address this issue, we present Local Universal Explainer (LUX), which is a rule-based explainer that can generate factual, counterfactual and visual explanations. It is based on a modified version of decision tree algorithms that allows for oblique splits and integration with feature importance XAI methods such as SHAP. It limits the use data generation in opposite to other algorithms, but is focused on selecting local concepts in a form of high-density clusters of real data that have the highest impact on forming the decision boundary of the explained model and generating artificial samples with novel SHAP-guided sampling algorithm. We tested our method on real and synthetic datasets and compared it with state-of-the-art rule-based explainers such as LORE, EXPLAN and Anchor. Our method outperforms the existing approaches in terms of simplicity, fidelity, representativeness, and consistency.