ESC-Rules: Explainable, Semantically Constrained Rule Sets
This addresses the need for interpretable AI in health decision-making, though it appears incremental as it builds on existing rule-based and fuzzy logic methods.
The paper tackles the problem of explainable prediction of continuous variables by learning fuzzy weighted rules with semantic constraints, achieving performance close to deep learning models while providing transparent explainability in a smoking cessation case study.
We describe a novel approach to explainable prediction of a continuous variable based on learning fuzzy weighted rules. Our model trains a set of weighted rules to maximise prediction accuracy and minimise an ontology-based 'semantic loss' function including user-specified constraints on the rules that should be learned in order to maximise the explainability of the resulting rule set from a user perspective. This system fuses quantitative sub-symbolic learning with symbolic learning and constraints based on domain knowledge. We illustrate our system on a case study in predicting the outcomes of behavioural interventions for smoking cessation, and show that it outperforms other interpretable approaches, achieving performance close to that of a deep learning model, while offering transparent explainability that is an essential requirement for decision-makers in the health domain.