SAT-Based Rigorous Explanations for Decision Lists
This addresses the need for interpretability in machine learning by providing efficient explanation methods for decision lists, which are widely used but can be opaque, though the approach is incremental as it builds on existing SAT-based techniques.
The paper tackles the problem of computing rigorous explanations for decision lists (DLs), showing that it is computationally hard, and proposes SAT-based encodings to efficiently compute abductive and contrastive explanations, with experimental results demonstrating feasibility for practical DLs.
Decision lists (DLs) find a wide range of uses for classification problems in Machine Learning (ML), being implemented in a number of ML frameworks. DLs are often perceived as interpretable. However, building on recent results for decision trees (DTs), we argue that interpretability is an elusive goal for some DLs. As a result, for some uses of DLs, it will be important to compute (rigorous) explanations. Unfortunately, and in clear contrast with the case of DTs, this paper shows that computing explanations for DLs is computationally hard. Motivated by this result, the paper proposes propositional encodings for computing abductive explanations (AXps) and contrastive explanations (CXps) of DLs. Furthermore, the paper investigates the practical efficiency of a MARCO-like approach for enumerating explanations. The experimental results demonstrate that, for DLs used in practical settings, the use of SAT oracles offers a very efficient solution, and that complete enumeration of explanations is most often feasible.