Regionally Additive Models: Explainable-by-design models minimizing feature interactions

TL;DR

Regionally Additive Models (RAMs) enhance explainability by identifying subregions where feature interactions are minimized, allowing for more accurate and interpretable models than traditional GAMs in complex ML tasks.

Contribution

The paper introduces RAMs, a novel approach that combines black-box models with regional analysis to improve interpretability and expressiveness over GAMs.

Findings

RAMs outperform GAMs in capturing complex feature interactions.

RAMs maintain interpretability while improving accuracy.

Experimental validation on synthetic and real datasets confirms effectiveness.

Abstract

Generalized Additive Models (GAMs) are widely used explainable-by-design models in various applications. GAMs assume that the output can be represented as a sum of univariate functions, referred to as components. However, this assumption fails in ML problems where the output depends on multiple features simultaneously. In these cases, GAMs fail to capture the interaction terms of the underlying function, leading to subpar accuracy. To (partially) address this issue, we propose Regionally Additive Models (RAMs), a novel class of explainable-by-design models. RAMs identify subregions within the feature space where interactions are minimized. Within these regions, it is more accurate to express the output as a sum of univariate functions (components). Consequently, RAMs fit one component per subregion of each feature instead of one component per feature. This approach yields a more expressive model compared to GAMs while retaining interpretability. The RAM framework consists of three steps. Firstly, we train a black-box model. Secondly, using Regional Effect Plots, we identify subregions where the black-box model exhibits near-local additivity. Lastly, we fit a GAM component for each identified subregion. We validate the effectiveness of RAMs through experiments on both synthetic and real-world datasets. The results confirm that RAMs offer improved expressiveness compared to GAMs while maintaining interpretability.