Graph Neural Network contextual embedding for Deep Learning on Tabular Data
This addresses the problem of improving deep learning performance on tabular data for industries leveraging AI, though it appears incremental as it builds on existing GNN methods.
The paper tackles the challenge of applying deep learning to tabular data by introducing a novel Graph Neural Network model for contextual embedding, which outperforms a recent deep learning benchmark on five public datasets and achieves competitive results against boosted-tree solutions.
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.