Pith. sign in

REVIEW 16 cited by

Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.09656 v3 pith:J5OGJAPX submitted 2023-10-14 cs.LG

Hengrui Zhang , Jiani Zhang , Balasubramaniam Srinivasan , Zhengyuan Shen , Xiao Qin , Christos Faloutsos , Huzefa Rangwala , George Karypis This is my paper · ORCID
classification cs.LG
keywords datatabulardiffusionlatentspacetabsyndistributionexisting
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces Tabsyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capture inter-column relations; (2) Quality: optimizing the distribution of latent embeddings to enhance the subsequent training of diffusion models, which helps generate high-quality synthetic data, (3) Speed: much fewer number of reverse steps and faster synthesis speed than existing diffusion-based methods. Extensive experiments on six datasets with five metrics demonstrate that Tabsyn outperforms existing methods. Specifically, it reduces the error rates by 86% and 67% for column-wise distribution and pair-wise column correlation estimations compared with the most competitive baselines.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RaMark: Radioactive Watermarking for Generated Tabular Data

    cs.CR 2026-07 conditional novelty 7.0 of 10

    A sinusoidal dependency embedded as part of the tabular distribution remains detectable after generative retraining and data-modification attacks while utility is preserved.

  2. NAE: Normalizing AutoEncoder

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A conditional surrogate loss that always picks the gradient estimate aligned with the reconstruction loss improves flow autoencoder training and reaches state-of-the-art generative performance on molecules, tabular da...

  3. LAB-Tab: LLM-Augmented Bayesian Network Adaptation for Few-Shot Tabular Generation

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A source-trained Bayesian network, augmented with LLM-proposed edges and calibrated by PPO, generates synthetic tabular data that outperforms six baselines in six ACS distribution-shift scenarios.

  4. FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents

    cs.LG 2026-07 conditional novelty 6.0 of 10

    FairDiffuseVQVAE reaches state-of-the-art fairness on the standard tabular benchmark (DPR 0.702, EOR 0.686) by uniform protected-attribute sampling at inference, paying ~15 AUC points of utility.

  5. Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A unified diffusion framework with per-modality noise clocks lets one model generate images, text, and tabular data jointly or conditionally in their native spaces.

  6. A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective

    cs.LG 2025-05 reject novelty 6.0 of 10

    A small subset of training samples drives most memorization in tabular diffusion models, and pruning them based on early memorization signals reduces measured leakage, though the evaluation metric makes part of the ga...

  7. LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    LLMSynthor iteratively prompts an LLM to propose corrective batches of micro-records, aligning synthetic data with target macro-statistics while preserving realistic joint dependencies.

  8. MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular Domains

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A regime-stratified benchmark of 196 tabular datasets shows that model rankings depend strongly on dataset characteristics such as sample size, feature correlation, and label imbalance.

  9. Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class

    cs.LG 2024-12 conditional novelty 6.0 of 10

    Adding an 'overlap' class label for boundary majority points during generative model training improves synthetic minority data quality and downstream classifier accuracy on imbalanced tabular data.

  10. A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

    cs.AI 2026-01 conditional novelty 5.0 of 10

    A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.

  11. Agents of Diffusion: Enhancing Diffusion Language Models with Multi-Agent Reinforcement Learning for Structured Data Generation (Extended Version)

    cs.MA 2026-01 reject novelty 5.0 of 10

    AoD pairs a frozen diffusion language model with two LLM agents that iteratively rewrite prompts from natural-language feedback, reporting better JSON diversity and validity, though the claimed RL mechanism and theore...

  12. Dependency-aware synthetic tabular data generation

    cs.LG 2025-07 conditional novelty 5.0 of 10

    HFGF improves preservation of functional and logical dependencies in synthetic tabular data by generating independent features and reconstructing dependent features from predefined mapping rules.

  13. The Prompt is Mightier than the Example

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Injecting domain knowledge into prompts can substitute for many in-context examples in LLM-based synthetic tabular data generation, cutting required example counts by 40-90%.

  14. Synthetic Tabular Data Generation: A Comparative Survey for Modern Techniques

    cs.LG 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes tabular data synthesis by generation objectives and adds a benchmark comparison of six models on Adult and CreditRisk.

  15. A Comprehensive Survey of Synthetic Tabular Data Generation

    cs.LG 2025-04 conditional novelty 3.0 of 10

    A structured survey that categorizes synthetic tabular data generation into traditional, diffusion, and LLM-based methods, with a comparative benchmark and a taxonomy of post-processing and evaluation.

  16. Synthetic Tabular Data: Methods, Attacks and Defenses

    cs.LG 2025-06 conditional novelty 1.0 of 10

    A review of tabular synthetic data generation, privacy attacks, and defenses, whose central message is that synthetic data alone does not guarantee privacy.

Pith tools