Universal Embeddings of Tabular Data
This addresses the need for flexible analysis of industrial tabular data, though it appears incremental as it builds on graph-based methods for embedding.
The paper tackles the problem of analyzing tabular data without predefined tasks by proposing a framework for generating task-independent embeddings, which transforms data into a graph structure and uses Graph Auto-Encoders to create embeddings that achieve superior performance compared to existing techniques.
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.