ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data

TL;DR

ZEUS introduces a zero-shot, unsupervised embedding method for clustering tabular data, eliminating the need for dataset-specific tuning and outperforming existing methods in speed and usability.

Contribution

It is the first zero-shot approach for generating embeddings for tabular data in an unsupervised manner, enabling effective clustering without additional training.

Findings

Performs on par or better than traditional clustering algorithms

Faster and more user-friendly than existing deep learning methods

Generalizes across various datasets without fine-tuning

Abstract

Clustering tabular data remains a significant open challenge in data analysis and machine learning. Unlike for image data, similarity between tabular records often varies across datasets, making the definition of clusters highly dataset-dependent. Furthermore, the absence of supervised signals complicates hyperparameter tuning in deep learning clustering methods, frequently resulting in unstable performance. To address these issues and reduce the need for per-dataset tuning, we adopt an emerging approach in deep learning: zero-shot learning. We propose ZEUS, a self-contained model capable of clustering new datasets without any additional training or fine-tuning. It operates by decomposing complex datasets into meaningful components that can then be clustered effectively. Thanks to pre-training on synthetic datasets generated from a latent-variable prior, it generalizes across various datasets without requiring user intervention. To the best of our knowledge, ZEUS is the first zero-shot method capable of generating embeddings for tabular data in a fully unsupervised manner. Experimental results demonstrate that it performs on par with or better than traditional clustering algorithms and recent deep learning-based methods, while being significantly faster and more user-friendly.