Deep Feature Embedding for Tabular Data
This addresses the challenge of capturing complex relationships in tabular data for machine learning applications, though it appears incremental in its approach.
The paper tackles the problem of limited embedding techniques for tabular data by proposing a novel deep embedding framework that uses lightweight neural networks to generate effective feature embeddings, achieving performance improvements on real-world datasets.
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.