mlsanityData to 14 Oct 2026

SOS: Score-based Oversampling for Tabular Data

arXiv 2206.08555 ↗First posted 17 Jun 2022cs.LG cs.AIcited by 29

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Score-based generative models (SGMs) are a recent breakthrough in generating fake images. SGMs are known to surpass other generative models, e.g., generative adversarial networks (GANs) and variational autoencoders (VAEs). Being inspired by their big success, in this work, we fully customize them for generating fake tabular data. In particular, we are interested in oversampling minor classes since imbalanced classes frequently lead to sub-optimal training outcomes. To our knowledge, we are the first presenting a score-based tabular data oversampling method. Firstly, we re-design our own score network since we have to process tabular data. Secondly, we propose two options for our generation method: the former is equivalent to a style transfer for tabular data and the latter uses the standard generative policy of SGMs. Lastly, we define a fine-tuning method, which further enhances the oversampling quality. In our experiments with 6 datasets and 10 baselines, our method outperforms other oversampling methods in all cases.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 21 of its 46 references that are in the map. First posted on arXiv 17 Jun 2022.

Builds on

21 of 46 references.

Closest ancestors · 4

Same direction, newest first

  1. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
  2. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  4. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 17

  1. 2017Improved Training of Wasserstein GANscited by 2,235
  2. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  3. 2019Modeling Tabular data using Conditional GANcited by 699
  4. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
  5. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  6. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  7. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  8. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  9. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  10. 2020Adversarial score matching and improved sampling for image generationcited by 96
  11. 2018BAGAN: Data Augmentation with Balancing GANcited by 90
  12. 2019Generative Adversarial Minority Oversamplingcited by 73
5 more
  1. 2020Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learningcited by 67
  2. 2018Banach Wasserstein GANcited by 56
  3. 2021OCT-GAN: Neural ODE-based Conditional Tabular GANscited by 27
  4. 2022Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesiscited by 24
  5. 2019Quality Aware Generative Adversarial Networkscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 8; 2025: 7; 2026: 3.

29 papers.

Sort:

By area:

  1. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  2. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  3. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  4. 2022STaSy: Score-based Tabular data Synthesiscited by 86
  5. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesiscited by 78
  6. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 63
  7. 2023TabuLa: Harnessing Language Models for Tabular Data Synthesiscited by 42
  8. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 28
  9. 2023Regular Time-series Generation using SGMcited by 23
  10. 2024Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AIcited by 15
  11. 2023CuTS: Customizable Tabular Synthetic Data Generationcited by 13
  12. 2023On the Usefulness of Synthetic Tabular Data Generationcited by 12
17 more
  1. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Datacited by 8
  2. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  3. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  4. 2024AIGT: AI Generative Table Based on Promptcited by 7
  5. 2025Diffusion Transformers for Tabular Data Time Series Generationcited by 5
  6. 2025Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmapcited by 5
  7. 2024Unmasking Trees for Tabular Datacited by 4
  8. 2025CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generationcited by 3
  9. 2025TSGM: Regular and Irregular Time-series Generation using Score-based Generative Modelscited by 3
  10. 2024DALL-M: Context-Aware Clinical Data Augmentation with LLMscited by 2
  11. 2025A Generalized Theory of Mixup for Structure-Preserving Synthetic Datacited by 2
  12. 2023MadSGM: Multivariate Anomaly Detection with Score-based Generative Modelscited by 1
  13. 2026TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusioncited by 1
  14. 2023Operator-learning-inspired Modeling of Neural Ordinary Differential Equationscited by 0
  15. 2024SEMRes-DDPM: Residual Network Based Diffusion Modelling Applied to Imbalanced Datacited by 0
  16. 2026From Noise to Order: Learning to Rank via Denoising Diffusioncited by 0
  17. 2026Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Tabular GANs for uneven distribution
  2. 2020Improved Techniques for Training Score-Based Generative Models
  3. 2024A Good Score Does not Lead to A Good Generative Model
  4. 2024Moderating the Generalization of Score-based Generative Model
  5. 2023Score Mismatching for Generative Modeling
  6. 2021Score-based Generative Modeling in Latent Space
  7. 2026Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
  8. 2024Multi-objective evolutionary GAN for tabular data synthesis