A Systematic Framework for Tabular Data Disentanglement

Ivan Tjuawinata; Andre Gunawan; Anh Quan Tran; Nitish Kumar; Payal Pote; Harsh Bansal; Chu-Hung Chi; Kwok-Yan Lam

cs.LGApr 9, 2026

A Systematic Framework for Tabular Data Disentanglement

Authors: Ivan Tjuawinata, Andre Gunawan, Anh Quan Tran, Nitish Kumar, Payal Pote, Harsh Bansal, Chu-Hung Chi, Kwok-Yan Lam,

Organizations: Nanyang Technological University, Singapore · Mastercard, India

Abstract

Tabular data, widely used in various applications such as industrial control systems, finance, and supply chain, often contains complex interrelationships among its attributes. Data disentanglement seeks to transform such data into latent variables with reduced interdependencies, facilitating more effective and efficient processing. Despite the extensive studies on data disentanglement over image, text, or audio data, tabular data disentanglement may require further investigation due to the more intricate attribute interactions typically found in tabular data. Moreover, due to the highly complex interrelationships, direct translation from other data domains results in suboptimal data disentanglement. Existing tabular data disentanglement methods, such as factor analysis, CT-GAN, and VAE face limitations including scalability issues, mode collapse, and poor extrapolation. In this paper, we propose the use of a framework to provide a systematic view on tabular data disentanglement that modularizes the process into four core components: data extraction, data modeling, model analysis, and latent representation extrapolation. We believe this work provides a deeper understanding of tabular data disentanglement and existing methods, and lays the foundation for potential future research in developing robust, efficient, and scalable data disentanglement techniques. Finally, we demonstrate the framework's applicability through a case study on synthetic tabular data generation, showcasing its potential in the particular downstream task of data synthesis.

Figures & tables

Figure 1: Proposed Framework of Tabular Data Disentanglement

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

	Average Precision Score	ROC-AUC Score
Initial Target Window $\mathcal{C}_{1}$ (baseline)
Original records	11.36%	81.82%
After record extraction	9.31%	79.77%
Enlarged Target Window $\mathcal{C}_{2}$
Original records	19.56%	91.20%
After record extraction	20.78%	91.70%

Appendix

Table 1: ML Efficacy results of our simple extraction protocol

Data Modelling Input Attributes	Mutual Information score
Original target attributes (5 Attributes)	3.9653
After Simple Attribute selection method (8 attributes)	4.0124
Including all Available Attributes (15 attributes)	4.0273

Appendix

Table 2: Average Mutual Information of latent variables on target window’s attributes

Disentangled Representation Learning

Disentangled representation learning separates distinct factors of variation so models can interpret, control, and generalize their predictions.

See all 231 papers

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion
Feb 26, 2026Donghong Cai, Jiarui Feng, Yanbo Wang +3Synthetic Tabular Data Generation Tabular Diffusion Models
Washington University in St. Louis · Peking University · Ant Group
Generating Benchmark Health Data Using a Tabular Diffusion Transformer
Aug 14, 2026Hao Yan, Lisa Pilgram, Dan Liu +3Synthetic Tabular Data Generation Tabular Diffusion Models
Children’s Hospital of Eastern Ontario Research Institute, Ontario, Canada · School of Epidemiology and Public Health, University of Ottawa, Ontario, Canada · Department of Nephrology and Medical Intensive Care, Charité - Universitaetsmedizin Berlin, Berlin, Germany +2
C $^{2}$ TC: A Training-Free Framework for Efficient Tabular Data Condensation
Feb 25, 2026Sijia Xu, Fan Li, Xiaoyang Wang +2Dataset Condensation Data-Efficient Learning
University of New South Wales, Australia · Shanghai Jiao Tong University, China

Feb 26, 2026J/K move · Enter open · S save

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

Donghong Cai, Jiarui Feng, Yanbo Wang, Da Zheng+2

Washington University in St. Louis · Peking University · Ant Group

Synthetic Tabular Data Generation Tabular Diffusion Models Multimodal Generation Continuous Diffusion Language Models

Open paper AskPDF arXiv

Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fields (e.g., reviews or clinical notes) alongside structured numerical and categorical attributes. Generating such heterogeneous tables with joint modeling of different modalities remains challenging. Existing approaches broadly fall into two categories: diffusion-based methods and LLM-based methods. Diffusion models can capture complex dependencies over numerical and categorical features in continuous or discrete spaces, but extending them to open-ended text is nontrivial and often leads to degraded text quality. In contrast, LLM-based generators naturally produce fluent text, yet their discrete tokenization can distort precise or wide-range numerical values, hindering accurate modeling of both numbers and language. In this work, we propose TabDLM, a unified framework for free-form tabular data generation via a joint numerical-language diffusion model built on masked diffusion language models (MDLMs). TabDLM models textual and categorical features through masked diffusion, while modeling numerical features with a continuous diffusion process through learned specialized numeric tokens embedding; bidirectional attention then captures cross-modality interactions within a single model. Extensive experiments on diverse benchmarks demonstrate the effectiveness of TabDLM compared to strong diffusion- and LLM-based baselines.

Abstract

Disentangled Representation Learning

Explore similar work

TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion

Generating Benchmark Health Data Using a Tabular Diffusion Transformer

C2^{2}2TC: A Training-Free Framework for Efficient Tabular Data Condensation

C $^{2}$ TC: A Training-Free Framework for Efficient Tabular Data Condensation