Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models · Xuezhou Zhang, S. Tan, +3 authors. R. Caruana ...
Oct 22, 2018 · Naive interpretation of multiclass GAMs can lead to false conclusions. Inspired by binary GAMs, we identify two axioms that any additive model ...
Missing: Harder | Show results with:Harder
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.
Missing: Harder | Show results with:Harder
This paper is one of the first to address interpretability challenges in the multiclass setting. ... Multiclass GAMs are hard to interpret fundamentally because ...
Missing: Harder | Show results with:Harder
Oct 22, 2018 · Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models. October 2018. Authors ...
Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive Models. Authors affiliations emails. Abstract.
Oct 22, 2018 · Drawing inspiration from binary GAMs, we identify two axioms that any additive model must satisfy to not be visually misleading. We then develop ...
Surprisingly, the natural interpretability of GAMs breaks down when there are more than two classes. Naive interpretation of multiclass GAMs can lead to false ...
A state-of-the-art GAM learning algorithm based on boosted trees is generalized to the multiclass setting, showing that this multiclass algorithm ...
Missing: Harder | Show results with:Harder
Figure 1 for Interpretability is Harder in the Multiclass Setting: Axiomatic Interpretability for Multiclass Additive. Generalized additive models (GAMs) are ...