**TabTransformer** is a deep tabular data modeling architecture for supervised and semi-supervised learning. The TabTransformer is built upon self-attention based Transformers. The Transformer layers transform the embeddings of categorical features into robust contextual embeddings to achieve higher prediction accuracy. 

As an overview, the architecture comprises a column embedding layer, a stack of $N$ [Transformer](/method/transformer) layers, and a multi-layer perceptron (MLP). The contextual embeddings (outputted by the Transformer layer) are concatenated along with continuous features which is inputted to an MLP. The loss function is then minimized  to learn all the parameters in an end-to-end learning.

**Cross-Covariance Attention**, or **XCA**, is an [attention mechanism](https://paperswithcode.com/methods/category/attention-mechanisms-1) which operates along the feature dimension instead of the token dimension as in [conventional transformers](https://paperswithcode.com/methods/category/transformers).

Using the definitions of queries, keys and values from conventional attention, the cross-covariance attention function is defined as:

$$
\text { XC-Attention }(Q, K, V)=V \mathcal{A}_{\mathrm{XC}}(K, Q), \quad \mathcal{A}\_{\mathrm{XC}}(K, Q)=\operatorname{Softmax}\left(\hat{K}^{\top} \hat{Q} / \tau\right)
$$

where each output token embedding is a convex combination of the $d\_{v}$ features of its corresponding token embedding in $V$. The attention weights $\mathcal{A}$ are computed based on the cross-covariance matrix.

Cross-Covariance Attention

XCiT: Cross-Covariance Image Transformers

TabTransformer

TabTransformer: Tabular Data Modeling Using Contextual Embeddings

The **Rectified Linear Unit N**, or **ReLUN**, is a modification of **[ReLU6](https://paperswithcode.com/method/relu6)** activation function that has trainable parameter **n**.

$$ReLUN(x) = min(max(0, x), n)$$

Source	TabTransformer: Tabular Data Modeling Using Contextual Embeddings
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com