# What is Imputation networks? Definition and meaning

Models trained to predict missing cells from the observed cells of the same row and table.

## Definition

**Imputation networks**: Models trained to predict missing cells from the observed cells of the same row and table.

In short: Neural networks that fill missing values.

## When it is used

Completing incomplete tables with confidence scores.

## Where it fits

Imputation networks belongs to **Large tabular foundation models** in the [Deep learning](/topics/deep-learning) topic. These are the other terms in the same group:

- **[Tabular foundation models](/glossary/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](/glossary/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](/glossary/tabpfn)**: A transformer pre-trained on synthetic datasets that predicts in a single forward pass with in-context learning.
- **[TabICL](/glossary/tabicl)**: A tabular foundation model that adds column-then-row attention to scale in-context learning to bigger datasets.
- **[TabSTAR](/glossary/tabstar)**: A tabular model that reads textual features through a pretrained language encoder together with numbers.
- **[XTab](/glossary/xtab)**: A framework that pre-trains shared transformer layers across many tables with table-specific embeddings.
- **[SAINT](/glossary/saint)**: A transformer that attends across features and across rows, with contrastive pre-training.
- **[FT-Transformer](/glossary/ft-transformer)**: Turns each feature into an embedding and processes them with a transformer.
- **[TabNet](/glossary/tabnet)**: A deep model that selects features step by step with sequential attention.
- **[Masked cell modeling](/glossary/masked-cell-modeling)**: The tabular counterpart of masked language modelling: random cells are masked and the model reconstructs them.

## Learn more

The full guide to **[Imputation networks](/tools/imputation-networks)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Iceberg compaction](/glossary/iceberg-compaction) · Next term: [In-context learning](/glossary/in-context-learning)
