mlsanityData to 7 Oct 2026

Stabilizing Training of Generative Adversarial Networks through Regularization

arXiv 1705.09367 ↗First posted 25 May 2017cs.LG stat.MLcited by 118

Not on the map. Why?

Abstract (arXiv)

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters. This fragility is in part due to a dimensional mismatch or non-overlapping support between the model distribution and the data distribution, causing their density ratio and the associated f-divergence to be undefined. We overcome this fundamental limitation and propose a new regularization approach with low computational cost that yields a stable GAN training procedure. We demonstrate the effectiveness of this regularizer across several architectures trained on common benchmark image generation tasks. Our regularization turns GAN models into reliable building blocks for deep learning.

Key facts. Cited by 118 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 34; 2022: 22; 2023: 20; 2024: 16; 2025: 15; 2026: 9.

118 papers.

Sort:

By area:

  1. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  2. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  3. 2025Diffusion Adversarial Post-Training for One-Step Video Generationcited by 142
  4. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 105
  5. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  6. 2021Generative Models as Distributions of Functionscited by 89
  7. 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generationcited by 84
  8. 2020Predicting Goal-directed Human Attention Using Inverse Reinforcement Learningcited by 53
  9. 2021Text to Image Generation with Semantic-Spatial Aware GANcited by 53
  10. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  11. 2023Better Generative Replay for Continual Federated Learningcited by 53
  12. 20213D Shape Generation with Grid-based Implicit Functionscited by 48
38 more
  1. 2023Class-Balancing Diffusion Modelscited by 47
  2. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  3. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  4. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 43
  5. 2021Context-Aware Layout to Image Generation with Enhanced Object Appearancecited by 41
  6. 2023Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transportcited by 39
  7. 2022Achieving Fairness at No Utility Cost via Data Reweighing with Influencecited by 38
  8. 2021EigenGAN: Layer-Wise Eigen-Learning for GANscited by 34
  9. 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
  10. 2021Statistical Analysis of Wasserstein Distributionally Robust Estimatorscited by 27
  11. 2024Training Unbiased Diffusion Models From Biased Datasetcited by 25
  12. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  13. 2024Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transportcited by 22
  14. 2021Representing 3D Shapes with Probabilistic Directed Distance Fieldscited by 21
  15. 2024Diffusive Gibbs Samplingcited by 21
  16. 2022SpoofGAN: Synthetic Fingerprint Spoof Imagescited by 17
  17. 2020Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learningcited by 15
  18. 2021Manifold Learning Benefits GANscited by 14
  19. 2021Learning quantum data with the quantum Earth Mover's distancecited by 13
  20. 2021A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensingcited by 13
  21. 2022AHP: Learning to Negative Sample for Hyperedge Predictioncited by 12
  22. 2025Adversarial Flow Modelscited by 10
  23. 2022Non-Iterative Recovery from Nonlinear Observations using Generative Modelscited by 9
  24. 2023PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendationcited by 9
  25. 2021Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascentcited by 8
  26. 2022Generalization Metrics for Practical Quantum Advantage in Generative Modelscited by 8
  27. 2022Interpretability Guarantees with Merlin-Arthur Classifierscited by 8
  28. 2023Nash Equilibria, Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimizationcited by 8
  29. 2023Analyzing and Improving Optimal-Transport-based Adversarial Networkscited by 8
  30. 2025DiffRatio: Training One-Step Diffusion Models Without Teacher Supervisioncited by 8
  31. 2022Generator Knows What Discriminator Should Learn in Unconditional GANscited by 7
  32. 2022DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Datacited by 7
  33. 2024Improving Neural Optimal Transport via Displacement Interpolationcited by 7
  34. 2025MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Trainingcited by 7
  35. 2023Matching aggregate posteriors in the variational autoencodercited by 6
  36. 2023On the Noise Scheduling for Generating Plausible Designs with Diffusion Modelscited by 6
  37. 2021Generative Convolution Layer for Image Generationcited by 5
  38. 2022Evaluating Graph Generative Models with Contrastively Learned Featurescited by 5

50 most cited of 118 All 118 (JSON)