Viet-Anh on Software Logo

What is: Neural Additive Model?

SourceNeural Additive Models: Interpretable Machine Learning with Neural Nets
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Neural Additive Models (NAMs) make restrictions on the structure of neural networks, which yields a family of models that are inherently interpretable while suffering little loss in prediction accuracy when applied to tabular data. Methodologically, NAMs belong to a larger model family called Generalized Additive Models (GAMs).

NAMs learn a linear combination of networks that each attend to a single input feature: each f_if\_{i} in the traditional GAM formulationis parametrized by a neural network. These networks are trained jointly using backpropagation and can learn arbitrarily complex shape functions. Interpreting NAMs is easy as the impact of a feature on the prediction does not rely on the other features and can be understood by visualizing its corresponding shape function (e.g., plotting f_i(x_i)f\_{i}\left(x\_{i}\right) vs. x_ix\_{i}).