Glossary · Deep learning
What is TabNet? Definition and meaning
A deep model that selects features step by step with sequential attention.
Definition
TabNet: A deep model that selects features step by step with sequential attention.
In short: Attentive interpretable tabular network.
When it is used
Tabular prediction with built-in feature selection.
Where it fits
TabNet belongs to Large tabular foundation models in the Deep learning topic. These are the other terms in the same group:
- Tabular foundation models: A large neural network pretrained across many tables so it can predict, impute or score new tables with little or no task-specific training.
- In-context learning: The ability of a trained model to perform a new task from examples or instructions in its input, without changing its weights.
- TabPFN: A transformer pre-trained on synthetic datasets that predicts in a single forward pass with in-context learning.
- TabICL: A tabular foundation model that adds column-then-row attention to scale in-context learning to bigger datasets.
- TabSTAR: A tabular model that reads textual features through a pretrained language encoder together with numbers.
- XTab: A framework that pre-trains shared transformer layers across many tables with table-specific embeddings.
- SAINT: A transformer that attends across features and across rows, with contrastive pre-training.
- FT-Transformer: Turns each feature into an embedding and processes them with a transformer.
- Masked cell modeling: The tabular counterpart of masked language modelling: random cells are masked and the model reconstructs them.
- Imputation networks: Models trained to predict missing cells from the observed cells of the same row and table.
Learn more
The full guide to TabNet explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.