mlsanityData to 7 Oct 2026

Fair Generative Modeling via Weak Supervision

arXiv 1910.12008 ↗First posted 26 Oct 2019cs.LG cs.CV stat.MLcited by 114

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine learning. We present a weakly supervised algorithm for overcoming dataset bias for deep generative models. Our approach requires access to an additional small, unlabeled reference dataset as the supervision signal, thus sidestepping the need for explicit labels on the underlying bias factors. Using this supplementary dataset, we detect the bias in existing datasets via a density ratio technique and learn generative models which efficiently achieve the twin goals of: 1) data efficiency by using training examples from both biased and reference datasets for learning; and 2) data generation close in distribution to the reference dataset at test time. Empirically, we demonstrate the efficacy of our approach which reduces bias w.r.t. latent factors by an average of up to 34.6% over baselines for comparable image generation using generative adversarial networks.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 25; 2023: 20; 2024: 28; 2025: 9; 2026: 11.

114 papers.

Sort:

By area:

  1. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  2. 2021EditGAN: High-Precision Semantic Image Editingcited by 156
  3. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  4. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  5. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  6. 2021Understanding and Evaluating Racial Biases in Image Captioningcited by 108
  7. 2022How to Backdoor Diffusion Models?cited by 102
  8. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  9. 2024Large-scale Reinforcement Learning for Diffusion Modelscited by 78
  10. 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Modelscited by 68
  11. 2022A Systematic Study of Bias Amplificationcited by 65
  12. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
38 more
  1. 2024Fairness Feedback Loops: Training on Synthetic Data Amplifies Biascited by 55
  2. 2021Directional Bias Amplificationcited by 54
  3. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  4. 2022Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifierscited by 53
  5. 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Modelscited by 50
  6. 2021Sample Selection for Fair and Robust Trainingcited by 48
  7. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  8. 2023Don't Play Favorites: Minority Guidance for Diffusion Modelscited by 37
  9. 2024CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?cited by 35
  10. 2021Featurized Density Ratio Estimationcited by 33
  11. 2022Fairness Reprogrammingcited by 33
  12. 2021Fairness for Image Generation with Uncertain Sensitive Attributescited by 31
  13. 2021Measuring Fairness in Generative Modelscited by 31
  14. 2022Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Modelscited by 28
  15. 2022Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Modelscited by 27
  16. 2022Fair Generative Models via Transfer Learningcited by 27
  17. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  18. 2024Training Unbiased Diffusion Models From Biased Datasetcited by 25
  19. 2021A Sociotechnical View of Algorithmic Fairnesscited by 24
  20. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  21. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  22. 2022The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devicescited by 21
  23. 2022Men Also Do Laundry: Multi-Attribute Bias Amplificationcited by 21
  24. 2022FairStyle: Debiasing StyleGAN2 with Style Channel Manipulationscited by 20
  25. 2024Self-Guided Generation of Minority Samples Using Diffusion Modelscited by 19
  26. 2024Constrained Diffusion Models via Dual Trainingcited by 19
  27. 2021Anatomizing Bias in Facial Analysiscited by 18
  28. 2023EHRDiff: Exploring Realistic EHR Synthesis with Diffusion Modelscited by 18
  29. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  30. 2023Model-Agnostic Gender Debiased Image Captioningcited by 17
  31. 2021Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Taskscited by 16
  32. 2023How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Studycited by 16
  33. 2023Quantifying Bias in Text-to-Image Generative Modelscited by 16
  34. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  35. 2023Improving Fair Training under Correlation Shiftscited by 14
  36. 2024Harm Amplification in Text-to-Image Modelscited by 14
  37. 2023Auditing and Generating Synthetic Data with Controllable Trust Trade-offscited by 13
  38. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12

50 most cited of 114 All 114 (JSON)