mlsanityData to 14 Oct 2026

Reducing Training Sample Memorization in GANs by Training with Memorization Rejection

arXiv 2210.12231 ↗First posted 21 Oct 2022cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Generative adversarial network (GAN) continues to be a popular research direction due to its high generation quality. It is observed that many state-of-the-art GANs generate samples that are more similar to the training set than a holdout testing set from the same distribution, hinting some training samples are implicitly memorized in these models. This memorization behavior is unfavorable in many applications that demand the generated samples to be sufficiently distinct from known samples. Nevertheless, it is unclear whether it is possible to reduce memorization without compromising the generation quality. In this paper, we propose memorization rejection, a training scheme that rejects generated samples that are near-duplicates of training samples during training. Our scheme is simple, generic and can be directly applied to any GAN architecture. Experiments on multiple datasets and GAN models validate that memorization rejection effectively reduces training sample memorization, and in many cases does not sacrifice the generation quality. Code to reproduce the experiment results can be found at texttthttps://github.com/jybai/MRGAN.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 40 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

32 of 40 references.

References · 32

  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  4. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  5. 2018Self-Attention Generative Adversarial Networkscited by 809
  6. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  7. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  8. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  9. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  10. 2016Revisiting Classifier Two-Sample Testscited by 268
  11. 2017Geometric GANcited by 233
  12. 2018Pros and Cons of GAN Evaluation Measurescited by 224
20 more
  1. 2018Do CIFAR-10 Classifiers Generalize to CIFAR-10?cited by 200
  2. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  3. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  4. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  5. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 107
  6. 2019Do We Train on Test Data? Purging CIFAR of Near-Duplicatescited by 62
  7. 2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
  8. 2020A Non-Parametric Test to Detect Data-Copying in Generative Modelscited by 52
  9. 2018Discriminator Rejection Samplingcited by 49
  10. 2016Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)cited by 44
  11. 2019Detecting Overfitting of Deep Generative Networks via Latent Recoverycited by 44
  12. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42
  13. 2022When do GANs replicate? On the choice of dataset sizecited by 34
  14. 2020Towards GAN Benchmarks Which Require Generalizationcited by 31
  15. 2017Approximation and Convergence Properties of Generative Adversarial Learningcited by 28
  16. 2015A Test of Relative Similarity For Model Selection in Generative Modelscited by 25
  17. 2021On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competitioncited by 18
  18. 2021Generalization Error of GAN from the Discriminator's Perspectivecited by 8
  19. 2019Investigating Under and Overfitting in Wasserstein Generative Adversarial Networkscited by 7
  20. 2020Toward a Generalization Metric for Deep Generative Modelscited by 5

Built on by

Cited by year

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

4 papers.

  1. 2025Memorization and Regularization in Generative Diffusion Modelscited by 40
  2. 2024ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generationcited by 13
  3. 2025Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyondcited by 6
  4. 2024Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Modelscited by 0