mlsanityData to 14 Oct 2026

FinDiff: Diffusion Models for Financial Tabular Data Generation

arXiv 2309.01472 ↗First posted 4 Sep 2023cs.LG q-fin.STcited by 41

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

Abstract (arXiv)

The sharing of microdata, such as fund holdings and derivative instruments, by regulatory institutions presents a unique challenge due to strict data confidentiality and privacy regulations. These challenges often hinder the ability of both academics and practitioners to conduct collaborative research effectively. The emergence of generative models, particularly diffusion models, capable of synthesizing data mimicking the underlying distributions of real-world data presents a compelling solution. This work introduces 'FinDiff', a diffusion model designed to generate real-world financial tabular data for a variety of regulatory downstream tasks, for example economic scenario modeling, stress tests, and fraud detection. The model uses embedding encodings to model mixed modality financial data, comprising both categorical and numeric attributes. The performance of FinDiff in generating synthetic tabular financial data is evaluated against state-of-the-art baseline models using three real-world financial datasets (including two publicly available datasets and one proprietary dataset). Empirical results demonstrate that FinDiff excels in generating synthetic tabular financial data with high fidelity, privacy, and utility.

Key facts. Cited by 41 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 26 of its 42 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

26 of 42 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Values2 Jul
  2. 2022TabDDPM: Modelling Tabular Data with Diffusion Models30 Sep

Other references · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2013Auto-Encoding Variational Bayescited by 4,053
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  11. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  12. 2022Diffusion Models in Vision: A Surveycited by 1,015
12 more
  1. 2019Modeling Tabular data using Conditional GANcited by 699
  2. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  3. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  4. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 265
  5. 2022Self-conditioned Embedding Diffusion for Text Generationcited by 117
  6. 2019Quant GANs: Deep Generation of Financial Time Seriescited by 108
  7. 2020Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learningcited by 67
  8. 2021Sig-Wasserstein GANs for Time Series Generationcited by 60
  9. 2022Empowering Diffusion Models on the Embedding Space for Text Generationcited by 40
  10. 2020Relational Data Synthesis using Generative Adversarial Networks: A Design Space Explorationcited by 21
  11. 2023A Survey of Diffusion Models in Natural Language Processingcited by 16
  12. 2019Adversarial Learning of Deepfakes in Accountingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 17; 2026: 12.

41 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 67
  2. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 28
  3. 2024In-Context Data Distillation with TabPFNcited by 19
  4. 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protectioncited by 16
  5. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 15
  6. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
  7. 2024Balanced Mixed-Type Tabular Data Synthesis with Diffusion Modelscited by 12
  8. 2025LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusioncited by 9
  9. 2025From Deep Learning to LLMs: A survey of AI in Quantitative Investmentcited by 9
  10. 2025Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphscited by 9
  11. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  12. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
29 more
  1. 2024FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generationcited by 7
  2. 2024Tabular Data Synthesis with Differential Privacy: A Surveycited by 6
  3. 2025Synthetic Data for Portfolios: A Throw of the Dice Will Never Abolish Chancecited by 4
  4. 2024The last Dance : Robust backdoor attack via diffusion models and bayesian approachcited by 3
  5. 2025TAGAL: Tabular Data Generation using Agentic LLM Methodscited by 3
  6. 2026Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Trainingcited by 3
  7. 2024Recurrent Neural Goodness-of-Fit Test for Time Seriescited by 2
  8. 2024Federated Diffusion Modeling with Differential Privacy for Tabular Data Synthesiscited by 2
  9. 2025Synthetic Tabular Data Detection In the Wildcited by 2
  10. 2025Evaluating Generative Models for Tabular Data: Novel Metrics and Benchmarkingcited by 2
  11. 2025LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Datacited by 2
  12. 2025Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Developmentcited by 2
  13. 2025Feature-aware Modulation for Learning from Temporal Tabular Datacited by 1
  14. 2026Latent Diffusion for Internet of Things Attack Data Generation in Intrusion Detectioncited by 1
  15. 2026TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusioncited by 1
  16. 2026OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scalecited by 1
  17. 2026SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generationcited by 1
  18. 2024Tokenize features, enhancing tables: the FT-TABPFN model for tabular classificationcited by 0
  19. 2024Cross-table Synthetic Tabular Data Detectioncited by 0
  20. 2025A Malliavin calculus approach to score functions in diffusion generative modelscited by 0
  21. 2025Boosting Predictive Performance on Tabular Data through Data Augmentation with Latent-Space Flow-Based Diffusioncited by 0
  22. 2025Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generationcited by 0
  23. 2026UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embeddingcited by 0
  24. 2026EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detectioncited by 0
  25. 2026Stable and Privacy-Preserving Synthetic Educational Data with Empirical Marginals: A Copula-Based Approachcited by 0
  26. 2026Generating Logically Consistent Synthetic Supply Chain Data with LLM-Driven Knowledge Graph Reasoningcited by 0
  27. 2026Constrained Tabular Diffusion for Financecited by 0
  28. 2026RaMark: Radioactive Watermarking for Generated Tabular Datacited by 0
  29. 2026Collaborative Synthetic Data for Privacy-Preserving Financial Fraud Detection Across Organizational Siloscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
  2. 2026MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
  3. 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges
  4. 2026TabSCM: A practical Framework for Generating Realistic Tabular Data
  5. 2023Boosting Data Analytics With Synthetic Volume Expansion
  6. 2024Beyond Monte Carlo: Harnessing Diffusion Models to Simulate Financial Market Dynamics
  7. 2025Flow Matching for Tabular Data Synthesis
  8. 2025Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection