Axiomatic Interpretability for Multiclass Additive Models
This addresses interpretability issues in multiclass GAMs for applications like healthcare, though it is incremental as it builds on existing binary GAM methods.
The paper tackles the problem of interpretability breakdown in multiclass generalized additive models (GAMs) by generalizing a boosted tree-based GAM learning algorithm to multiclass settings and developing Additive Post-Processing for Interpretability (API), which transforms models to satisfy interpretability axioms without accuracy loss, demonstrating effectiveness on a 12-class infant mortality dataset.
Generalized additive models (GAMs) are favored in many regression and binary classification problems because they are able to fit complex, nonlinear functions while still remaining interpretable. In the first part of this paper, we generalize a state-of-the-art GAM learning algorithm based on boosted trees to the multiclass setting, and show that this multiclass algorithm outperforms existing GAM learning algorithms and sometimes matches the performance of full complexity models such as gradient boosted trees. In the second part, we turn our attention to the interpretability of GAMs in the multiclass setting. Surprisingly, the natural interpretability of GAMs breaks down when there are more than two classes. Naive interpretation of multiclass GAMs can lead to false conclusions. Inspired by binary GAMs, we identify two axioms that any additive model must satisfy in order to not be visually misleading. We then develop a technique called Additive Post-Processing for Interpretability (API), that provably transforms a pre-trained additive model to satisfy the interpretability axioms without sacrificing accuracy. The technique works not just on models trained with our learning algorithm, but on any multiclass additive model, including multiclass linear and logistic regression. We demonstrate the effectiveness of API on a 12-class infant mortality dataset.