Modern Deep Learning for Tabular Data: Novel Approaches to Common Modeling Problems

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2023

A. Ye, Z. WangModern Deep Learning for Tabular Datahttps://doi.org/10.1007/978-1-4842-8692-0_7

7. Tree-Based Deep Learning Approaches

Andre Ye¹   and Zian Wang²

(1)

Seattle, WA, USA

(2)

Redmond, WA, USA

 

Imitation is the most sincere form of flattery.

—Oscar Wilde, Irish Poet, among many others

In this last chapter of Part 2, we explore deep models that draw upon the success of tree-based models to inform their architectures and training processes. Together with attention-based models, this constitutes the majority of current tabular deep learning research. Tree-based models are well-adapted toward many domains of tabular data because of their sharp and rigidly ...