cs.LGSep 30, 2026

CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data

Authors: Mohamed Amine Ketata, Maximilian Schambach, Stephan Günnemann

Organizations: Munich Data Science Institute, Technical University of Munich, Germany · SAP SE, Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many specialized models. In this paper, we introduce CDMD, a tabular diffusion model trained jointly across heterogeneous datasets with different schemas and variable numbers of numerical and categorical features. Unlike existing cross-dataset tabular diffusion models that operate in continuous representation spaces, CDMD defines diffusion directly over the mixed-type feature space and is trained end-to-end. To accommodate heterogeneous categorical domains, we introduce a schema-restricted reverse-process parameterization for masked diffusion models, in which the output space dynamically adapts to each feature's vocabulary. We then compose numerical and categorical feature-level diffusion processes into a schema-dependent row-level process. A shared schema-aware Transformer denoiser captures dependencies between features and parameterizes the reverse process across varying schemas. On seven real-world datasets, a single jointly trained CDMD achieves the highest average generation quality among strong single-dataset and cross-dataset baselines, while using substantially fewer total parameters than the collection of separately trained models. Furthermore, pre-training on a corpus of 337 datasets improves generation on previously unseen datasets under both limited target data and limited adaptation epochs. These results demonstrate the potential of direct mixed-type diffusion for shared and transferable tabular data generation. Our code is available at https://github.com/ketatam/cdmd.

Figures & tables

Table 1: In-domain cross-dataset generation results (Section 4.1 ). Entries report mean ±\scriptstyle\pm standard deviation over three runs. Average is the mean over datasets. Train Set is the real-data reference. Bold and underlined entries mark the best and second-best scores in each column, excluding Train Set . GReaT cannot be applied to News because of its maximum length limit.
Figure 1: Sample-constrained generation results: Overall Evaluation Score ( SS ) vs. the number of target training rows. Lines and shaded regions show the mean ±\scriptstyle\pm standard deviation over five runs using independently-sampled target training subsets. The final panel shows the mean across datasets.
Figure 2: Epoch-constrained generation results: Overall Evaluation Score ( SS ) vs. training epochs. Lines and shaded regions indicate the mean ±\scriptstyle\pm standard deviation over three runs.
Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 3: Overview of CDMD . Numerical features are corrupted with Gaussian noise, while categorical features are randomly masked. The tokenizer combines each noisy feature with schema information, and a shared transformer encoder captures dependencies across columns. A shared MLP predicts clean numerical values, while a shared transformer decoder uses category embeddings and the contextualized feature token to produce probabilities over each categorical column’s valid vocabulary. These predictions guide the mixed-type reverse diffusion process. The schema determines the number of feature tokens and categorical outputs, while parameters are shared across datasets and columns of the same type, allowing a single model to handle heterogeneous tables.
Dataset# Train Rows# Test Rows# Cols# Num# Cat# Max CatTask
Adult24,42124,421156942Binary
Default15,00015,00024141011Binary
Magic9,5109,510111012Binary
Shoppers6,1656,1651810820Binary
Diabetes50,88350,8833782966Multiclass
Beijing20,87820,8798714Regression
Appendix
Table 2: Evaluation dataset statistics. Numerical and categorical column counts include the target. Max Cat denotes the cardinality of the largest categorical vocabulary; Binary denotes binary classification.
QuantityMeanMedianMinMaxSum
# Rows28,58510,99910100,0009,633,139
# Cols11.1102333,734
# Num7.360282,458
# Cat3.820231,276
Total datasets: 337
Appendix
Table 3: Pretraining dataset summary across the 337 datasets.
Figure 4: Distribution of row counts and total, numerical, and categorical column counts across the 337 pre-training datasets. Each dataset contributes one observation, and column counts reflect retained features after preprocessing. Row counts use 50 logarithmically spaced bins; column counts use one bin per integer.
Table 4: In-domain cross-dataset generation results for the three evaluation axes
Table 5: In-domain cross-dataset generation results for the four individual metrics of Fidelity.
Table 6: In-domain cross-dataset generation results for Privacy.
Figure 5: Few-shot performance across seven datasets and their cross-dataset average. Curves show mean performance, and shaded regions indicate one standard deviation across seeds.
Figure 6: Few-epoch performance across seven datasets and their cross-dataset average. Curves show mean performance, and shaded regions indicate one standard deviation across seeds.

Explore similar work

CardsList

  1. MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation

    Sep 30, 2026Pengfei Li, Mohammad KhalilTabular DataTemporal Dependence

    Centre for the Science of Learning & Technology (SLATE), University of Bergen, Bergen, Norway

  2. Geometry-Aware Tabular Diffusion

    May 23, 2026David Turtora ZagardoGenerative ArchitecturesIterative Denoising Methods

    Independent Researcher.

  3. FUSE: Feature-Wise Unified Specialization with Cross-Column Exchange for Mixed-Type Tabular Flow Matching

    Aug 7, 2026Suman Cha, Seongchan Lee, Dohyun Ko +1Conditional Flow MatchingMixture Models

    Department of Statistics and Data Science, Yonsei University · Department of Mathematical Sciences, KAIST