Deep Feature Embedding for Tabular Data

TL;DR

This paper introduces a novel deep embedding framework for tabular data that effectively captures complex relationships in numerical and categorical features using lightweight neural networks, improving representation quality.

Contribution

It presents a new deep embedding method combining feature expansion, deep transformation, and a unique lookup-based embedding for categorical data, advancing tabular data learning techniques.

Findings

Enhanced embedding quality for numerical features.

Effective categorical feature representation via deep lookup embeddings.

Improved performance on real-world datasets.

Abstract

Tabular data learning has extensive applications in deep learning but its existing embedding techniques are limited in numerical and categorical features such as the inability to capture complex relationships and engineering. This paper proposes a novel deep embedding framework with leverages lightweight deep neural networks to generate effective feature embeddings for tabular data in machine learning research. For numerical features, a two-step feature expansion and deep transformation technique is used to capture copious semantic information. For categorical features, a unique identification vector for each entity is referred by a compact lookup table with a parameterized deep embedding function to uniform the embedding size dimensions, and transformed into a embedding vector using deep neural network. Experiments are conducted on real-world datasets for performance evaluation.