XBNet : An Extremely Boosted Neural Network

TL;DR

This paper introduces XBNet, a novel neural network architecture that combines tree-based models with neural networks, optimized by Boosted Gradient Descent, to improve performance and interpretability on tabular data.

Contribution

The paper presents a new architecture, XBNet, integrating tree models with neural networks and a novel optimization method for better tabular data handling.

Findings

Improved performance on tabular datasets.

Enhanced interpretability of neural network models.

Effective training via Boosted Gradient Descent.

Abstract

Neural networks have proved to be very robust at processing unstructured data like images, text, videos, and audio. However, it has been observed that their performance is not up to the mark in tabular data; hence tree-based models are preferred in such scenarios. A popular model for tabular data is boosted trees, a highly efficacious and extensively used machine learning method, and it also provides good interpretability compared to neural networks. In this paper, we describe a novel architecture XBNet, which tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data which increases its interpretability and performance.