GA²M
An extension of the Generalized Additive Model (GAM) that augments univariate shape functions with pairwise interaction terms to capture synergistic effects between features. GA²M belongs to the family of glass-box models, meaning its structure and learned components remain fully interpretable and can be examined to understand how individual features and feature pairs contribute to predictions.
Timeline (last 90 days)
The interpretability of GA²M (generalized additive model with pairwise interactions) relies on visualizing each pairwise shape function as a contour plot.
EBM (Explainable Boosting Machine) is an efficient implementation of GA²M that uses boosted trees to learn shape functions and then converts them into lookup tables.
BAM (bivariate additive model) belongs to the GA²M family, and its core constraint is that every pairwise shape function is restricted to an asymmetric bivariate Gaussian distribution.
The paper conducted experiments on six tabular benchmark datasets, and the results show that BAM's prediction accuracy is comparable to standard GAM and close to the level of GA²M.
All Facts (4)
The interpretability of GA²M (generalized additive model with pairwise interactions) relies on visualizing each pairwise shape function as a contour plot.
50%UnverifiedEBM (Explainable Boosting Machine) is an efficient implementation of GA²M that uses boosted trees to learn shape functions and then converts them into lookup tables.
50%UnverifiedBAM (bivariate additive model) belongs to the GA²M family, and its core constraint is that every pairwise shape function is restricted to an asymmetric bivariate Gaussian distribution.
50%UnverifiedThe paper conducted experiments on six tabular benchmark datasets, and the results show that BAM's prediction accuracy is comparable to standard GAM and close to the level of GA²M.
50%