SAINT is a hybrid deep learning approach to solving tabular data problems. SAINT performs attention over both rows and columns, and it includes an enhanced embedding method. The architecture, pre-training and training pipeline are as follows:
Paper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
CutMix
|
Image Data Augmentation | |
Feedforward Network
|
Feedforward Networks | |
Mixup
|
Image Data Augmentation |