Universal Embeddings of Tabular Data

TL;DR

This paper introduces a task-independent embedding framework for tabular data that transforms tables into graphs and uses graph auto-encoders to generate universal embeddings, enabling various downstream tasks without retraining.

Contribution

The novel approach converts tabular data into graph structures and employs graph auto-encoders to produce universal embeddings applicable to multiple tasks.

Findings

Outperforms existing universal tabular embedding methods

Embeddings enable effective regression, classification, and outlier detection

Unseen samples can be embedded without additional training

Abstract

Tabular data in relational databases represents a significant portion of industrial data. Hence, analyzing and interpreting tabular data is of utmost importance. Application tasks on tabular data are manifold and are often not specified when setting up an industrial database. To address this, we present a novel framework for generating universal, i.e., task-independent embeddings of tabular data for performing downstream tasks without predefined targets. Our method transforms tabular data into a graph structure, leverages Graph Auto-Encoders to create entity embeddings, which are subsequently aggregated to obtain embeddings for each table row, i.e., each data sample. This two-step approach has the advantage that unseen samples, consisting of similar entities, can be embedded without additional training. Downstream tasks such as regression, classification or outlier detection, can then be performed by applying a distance-based similarity measure in the embedding space. Experiments on real-world datasets demonstrate that our method achieves superior performance compared to existing universal tabular data embedding techniques.