Methods › General › Deep Tabular Learning

Deep Tabular Learning

27 methods 1,237 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 26 of the 27 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.

Text 1, carried by 25 of 27 methods:

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,...

Text 2, carried by 1 of 27 methods:

Transformers are a type of neural network architecture that have several properties that make them effective for modeling data with long-range dependencies. They generally feature a combination of multi-headed attention mechanisms, residual connections, layer normalization, feedforward connections, and positional embeddings.

Methods

All 27 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.


BiLSTM Bidirectional LSTM	2001	657
NON Network On Network	–	389
NODE Neural Oblivious Decision Ensembles	–	42
TabNet	–	29
TABPFN tabular data Prior-data Fitted Network	–	26
MATE	–	14
ODL online deep learning	–	11
FT-Transformer	–	10
SAINT	–	9
TabTransformer	–	9
SCARF	–	7
Wide&Deep	–	7
GRANDE Gradient-Based Decision Tree Ensembles	–	5
Hierarchical MTL Hierarchical Multi-Task Learning	–	5
GANDALF Gated Adaptive Network for Deep Automated Learning of Features	–	4
DCN-V2	–	3
TURL TURL: Table Understanding through Representation Learning	–	3
TaBERT	–	3
ARM-Net	–	2
AutoInt	–	2
DNN2LR	–	2
Boost-GNN	–	1
GrowNet	–	1
StruBERT StruBERT: Structure-aware BERT for Table Search and Matching	–	1
TABBIE	–	1
TabNN	–	1
VIME Value Imputation and Mask Estimation	–	1