Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Feature Embedding for Tabular Data

Yuqian Wu, Hengyi Luo, Raymond S. T. Lee

TL;DR

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.

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.

Deep Feature Embedding for Tabular Data

TL;DR

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.

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.
Paper Structure (16 sections, 4 equations, 4 figures, 5 tables)

This paper contains 16 sections, 4 equations, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Deep Feature Embedding
  5. Numerical Feature Embedding
  6. Deep Embedding for Numerical Feature
  7. Categorical Feature Embedding
  8. Deep Embedding for Categorical Feature
  9. Experiments
  10. Experimental Setup
  11. Overall Prediction Performance with Various Embedding Methods in ARM-Net Model
  12. Comparing DL models and GBDT
  13. The Impact of Deep Transformation Layer Number on Model Performance
  14. Ablation study
  15. Conclusion
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Deep numerical feature embedding framework.
  • Figure 2: Deep categorical feature embedding framework.
  • Figure 3: Impact of Embedding Size on AUC Improvement for ARM-Net with Our Deep Embedding Framework on Frappe and Diabetes$_{130}$ datasets
  • Figure 4: Impact of Deep Transformation Layer size on ARM-Net Performance: AUC Evaluation on Frappe and Diabetes$_{130}$.