Graph Neural Network contextual embedding for Deep Learning on Tabular Data

TL;DR

This paper introduces a novel Graph Neural Network-based deep learning model for tabular data, leveraging feature interactions to improve performance over traditional models and benchmarks.

Contribution

It proposes a new GNN-based deep learning approach specifically designed for tabular data, addressing the challenge of modeling feature interactions.

Findings

Outperforms recent DL benchmarks on five public datasets

Achieves competitive results compared to boosted-tree models

Demonstrates the effectiveness of GNNs for tabular data modeling

Abstract

All industries are trying to leverage Artificial Intelligence (AI) based on their existing big data which is available in so called tabular form, where each record is composed of a number of heterogeneous continuous and categorical columns also known as features. Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing, but its applicability to tabular data has been more challenging. More classical Machine Learning (ML) models like tree-based ensemble ones usually perform better. This paper presents a novel DL model using Graph Neural Network (GNN) more specifically Interaction Network (IN), for contextual embedding and modelling interactions among tabular features. Its results outperform those of a recently published survey with DL benchmark based on five public datasets, also achieving competitive results when compared to boosted-tree solutions.