mlsanityData to 7 Oct 2026

Beyond Statistical Co-occurrence: Unlocking Intrinsic Semantics for Tabular Data Clustering

arXiv 2604.10865 ↗First posted 13 Apr 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Clustering (DC) has emerged as a powerful tool for tabular data analysis in real-world domains like finance and healthcare. However, most existing methods rely on data-level statistical co-occurrence to infer the latent metric space, often overlooking the intrinsic semantic knowledge encapsulated in feature names and values. As a result, semantically related concepts like `Flu' and `Cold' are often treated as symbolic tokens, causing conceptually related samples to be isolated. To bridge the gap between dataset-specific statistics and intrinsic semantic knowledge, this paper proposes Tabular-Augmented Contrastive Clustering (TagCC), a novel framework that anchors statistical tabular representations to open-world textual concepts. Specifically, TagCC utilizes Large Language Models (LLMs) to distill underlying data semantics into textual anchors via semantic-aware transformation. Through Contrastive Learning (CL), the framework enriches the statistical tabular representations with the open-world semantics encapsulated in these anchors. This CL framework is jointly optimized with a clustering objective, ensuring that the learned representations are both semantically coherent and clustering-friendly. Extensive experiments on benchmark datasets demonstrate that TagCC significantly outperforms its counterparts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

25 of 36 references.

References · 25

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  3. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  4. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  5. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  6. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  7. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 420
  8. 2022TabLLM: Few-shot Classification of Tabular Data with Large Language Modelscited by 273
  9. 2020Contrastive Clusteringcited by 264
  10. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
  11. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  12. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
13 more
  1. 2020Structural Deep Clustering Networkcited by 145
  2. 2022TransTab: Learning Transferable Tabular Transformers Across Tablescited by 132
  3. 2021Deep Graph Clustering via Dual Correlation Reductioncited by 97
  4. 2022Deep Clustering: A Comprehensive Surveycited by 78
  5. 2022A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directionscited by 73
  6. 2017The Impact of Random Models on Clustering Similaritycited by 34
  7. 2023Deep Multiview Clustering by Contrasting Cluster Assignmentscited by 33
  8. 2023Interpretable Deep Clustering for Tabular Datacited by 19
  9. 2024A Survey on Self-Supervised Learning for Non-Sequential Tabular Datacited by 15
  10. 2023Deep Clustering of Tabular Data by Weighted Gaussian Distribution Learningcited by 12
  11. 2024TableDC: Deep Clustering for Tabular Datacited by 9
  12. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  13. 2026Learning Unified Distance Metric for Heterogeneous Attribute Data Clusteringcited by 4

Built on by

Not cited yet.