SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
This work addresses the challenge of applying deep learning effectively to tabular data, which is crucial for applications such as fraud detection and healthcare, representing a significant advancement over existing methods.
The paper tackled the problem of improving deep learning performance on tabular data by introducing SAINT, a hybrid method using row and column attention with enhanced embeddings and contrastive pre-training for label-scarce scenarios, which outperformed previous deep learning methods and gradient boosting techniques like XGBoost on average across benchmarks.
Tabular data underpins numerous high-impact applications of machine learning from fraud detection to genomics and healthcare. Classical approaches to solving tabular problems, such as gradient boosting and random forests, are widely used by practitioners. However, recent deep learning methods have achieved a degree of performance competitive with popular techniques. We devise a hybrid deep learning approach to solving tabular data problems. Our method, SAINT, performs attention over both rows and columns, and it includes an enhanced embedding method. We also study a new contrastive self-supervised pre-training method for use when labels are scarce. SAINT consistently improves performance over previous deep learning methods, and it even outperforms gradient boosting methods, including XGBoost, CatBoost, and LightGBM, on average over a variety of benchmark tasks.