mlsanityData to 14 Oct 2026

ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models

arXiv 2405.17724 ↗First posted 28 May 2024cs.AIcited by 28

On the map: Diffusion models → Flow matching, time series and science

also in 1 more
Abstract (arXiv)

Recent research in tabular data synthesis has focused on single tables, whereas real-world applications often involve complex data with tens or hundreds of interconnected tables. Previous approaches to synthesizing multi-relational (multi-table) data fall short in two key aspects: scalability for larger datasets and capturing long-range dependencies, such as correlations between attributes spread across different tables. Inspired by the success of diffusion models in tabular data modeling, we introduce Cluster Latent Variable guided Denoising Diffusion Probabilistic Models (ClavaDDPM). This novel approach leverages clustering labels as intermediaries to model relationships between tables, specifically focusing on foreign key constraints. ClavaDDPM leverages the robust generation capabilities of diffusion models while incorporating efficient algorithms to propagate the learned latent variables across tables. This enables ClavaDDPM to capture long-range dependencies effectively. Extensive evaluations on multi-table datasets of varying sizes show that ClavaDDPM significantly outperforms existing methods for these long-range dependencies while remaining competitive on utility metrics for single-table data.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 30 of its 54 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

30 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space14 Oct
  2. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis25 Apr
  3. 2022Diffusion models for missing value imputation in tabular data31 Oct
  4. 2022STaSy: Score-based Tabular data Synthesis8 Oct
  5. 2022TabDDPM: Modelling Tabular Data with Diffusion Models30 Sep

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  8. 2019Modeling Tabular data using Conditional GANcited by 699
  9. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  10. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 196
  11. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  12. 2022Differentially Private Diffusion Modelscited by 119
13 more
  1. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  2. 2020Synthetic Data -- Anonymisation Groundhog Daycited by 108
  3. 2023Generative models improve fairness of medical classifiers under distribution shiftscited by 90
  4. 2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 86
  5. 2023Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Datacited by 32
  6. 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
  7. 2020Kamino: Constraint-Aware Differentially Private Data Synthesiscited by 25
  8. 2023Synthetic Data Applications in Financecited by 22
  9. 2023PrivLava: Synthesizing Relational Data with Foreign Keys under Differential Privacycited by 11
  10. 2017Size bounds and query plans for relational joinscited by 10
  11. 2022Generating Realistic Synthetic Relational Data through Graph Variational Autoencoderscited by 8
  12. 2014Fast Learning of Relational Dependency Networkscited by 3
  13. 2023Differentially Private Data Release over Multiple Tablescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 13.

28 papers.

Sort:

By area:

  1. 2026PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Modelscited by 19
  2. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 14
  3. 2025The DCR Delusion: Measuring the Privacy Risk of Synthetic Datacited by 11
  4. 2025Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesiscited by 10
  5. 2025Joint Relational Database Generation via Graph-Conditional Diffusion Modelscited by 9
  6. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  7. 2024Benchmarking the Fidelity and Utility of Synthetic Relational Datacited by 7
  8. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 6
  9. 2025RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Modelscited by 4
  10. 2025MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Datacited by 4
  11. 2025Graph-Conditional Flow Matching for Relational Data Generationcited by 3
  12. 2024Differentially Private Synthetic Data Generation for Relational Databasescited by 2
16 more
  1. 2025Membership Inference over Diffusion-models-based Synthetic Tabular Datacited by 2
  2. 2026Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Settingcited by 2
  3. 2026MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular datacited by 2
  4. 2026Differentially Private Synthetic Data via APIs 4: Tabular Datacited by 2
  5. 2025TAMIS: Tailored Membership Inference Attacks on Synthetic Datacited by 1
  6. 2025Democratizing Tabular Data Access with an Openunicodex2013Source Syntheticunicodex2013Data SDKcited by 1
  7. 2026Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspectivecited by 1
  8. 2025Towards Synthesizing High-Dimensional Tabular Data with Limited Samplescited by 0
  9. 2025Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessingcited by 0
  10. 2026On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metricscited by 0
  11. 2026FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Modelscited by 0
  12. 2026Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Losscited by 0
  13. 2026Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Datacited by 0
  14. 2026PluRel-to-RDB-PFN: Schema-Guided Synthetic Relational Pretrainingcited by 0
  15. 2026Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Datacited by 0
  16. 2026Beyond Marginals: A Multi-Dimensional Evaluation Framework for Multi-Table Synthetic Data Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
  2. 2026CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Data
  3. 2023AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
  4. 2025TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
  5. 2024CTSyn: A Foundation Model for Cross Tabular Data Generation
  6. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis
  7. 2025LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
  8. 2026Geometry-Aware Tabular Diffusion