Consists of tabular data learning approaches that use deep learning architectures for learning on tabular data. According to the taxonomy in V.Borisov et al. (2021), deep learning approaches for tabular data can be categorized into:

• Regularization models
• Transformer-based models: TabNet, TabTransformer, SAINT, ARM-Net,...
• Hybrid models (fully differentiable and partly differentiable): Wide&Deep, TabNN, NON, Boost-GNN, NODE,...
• Data encoding methods (single-dimensional encoding and multi-dimensional encoding): VIME, SCARF,...