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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Marszałek, Patryk, Kuśmierczyk, Tomasz, Wydmański, Witold, Tabor, Jacek, Śmieja, Marek
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915572956004352
author Marszałek, Patryk
Kuśmierczyk, Tomasz
Wydmański, Witold
Tabor, Jacek
Śmieja, Marek
author_facet Marszałek, Patryk
Kuśmierczyk, Tomasz
Wydmański, Witold
Tabor, Jacek
Śmieja, Marek
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10704
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Marszałek, Patryk
Kuśmierczyk, Tomasz
Wydmański, Witold
Tabor, Jacek
Śmieja, Marek
Machine Learning
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.
title ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
topic Machine Learning
url https://arxiv.org/abs/2505.10704