SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

06/02/2021
by   Gowthami Somepalli, et al.
1

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.

READ FULL TEXT

page 9

page 18

research
11/04/2021

Leveraging Time Irreversibility with Order-Contrastive Pre-training

Label-scarce, high-dimensional domains such as healthcare present a chal...
research
10/15/2021

Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science

Deep learning techniques have been increasingly applied to the natural s...
research
06/01/2022

Hopular: Modern Hopfield Networks for Tabular Data

While Deep Learning excels in structured data as encountered in vision a...
research
07/24/2023

FaFCNN: A General Disease Classification Framework Based on Feature Fusion Neural Networks

There are two fundamental problems in applying deep learning/machine lea...
research
04/21/2022

PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map

Deep learning has recently achieved significant progress in trajectory f...
research
11/14/2016

Post Training in Deep Learning with Last Kernel

One of the main challenges of deep learning methods is the choice of an ...
research
11/30/2015

Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning

Deep learning has been one of the most prominent machine learning techni...

Please sign up or login with your details

Forgot password? Click here to reset