mlsanityData to 7 Oct 2026

Memorization in deep learning: A survey

arXiv 2406.03880 ↗First posted 6 Jun 2024cs.LG cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remains a significant challenge. Recent investigations have uncovered an interesting memorization phenomenon in which DNNs tend to memorize specific details from examples rather than learning general patterns, affecting model generalization, security, and privacy. This raises critical questions about the nature of generalization in DNNs and their susceptibility to security breaches. In this survey, we present a systematic framework to organize memorization definitions based on the generalization and security/privacy domains and summarize memorization evaluation methods at both the example and model levels. Through a comprehensive literature review, we explore DNN memorization behaviors and their impacts on security and privacy. We also introduce privacy vulnerabilities caused by memorization and the phenomenon of forgetting and explore its connection with memorization. Furthermore, we spotlight various applications leveraging memorization and forgetting mechanisms, including noisy label learning, privacy preservation, and model enhancement. This survey offers the first-in-kind understanding of memorization in DNNs, providing insights into its challenges and opportunities for enhancing AI development while addressing critical ethical concerns.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 114 of its 156 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

114 of 156 references.

References · 114

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2016Deep Learning with Differential Privacycited by 2,682
  11. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  12. 2016Learning without Forgettingcited by 2,465
38 more
  1. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2019Language Models as Knowledge Bases?cited by 1,922
  7. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  10. 2014How transferable are features in deep neural networks?cited by 1,216
  11. 2022Planning-oriented Autonomous Drivingcited by 1,068
  12. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  13. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  14. 2022Mass-Editing Memory in a Transformercited by 976
  15. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  16. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  17. 2017A Closer Look at Memorization in Deep Networkscited by 936
  18. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  19. 2021Membership Inference Attacks From First Principlescited by 839
  20. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  21. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  22. 2023Extracting Training Data from Diffusion Modelscited by 723
  23. 2014Certifying and removing disparate impactcited by 715
  24. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 713
  25. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  26. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 669
  27. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  28. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  29. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  30. 2021Editing Factual Knowledge in Language Modelscited by 548
  31. 2019Benign Overfitting in Linear Regressioncited by 544
  32. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 522
  33. 2020Overfitting in adversarially robust deep learningcited by 504
  34. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  35. 2021Fast Model Editing at Scalecited by 491
  36. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 452
  37. 2022Memory-Based Model Editing at Scalecited by 443
  38. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414

50 most cited of 114 All 114 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 7; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024Undesirable Memorization in Large Language Models: A Surveycited by 29
  2. 2024From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classificationcited by 7
  3. 2025Are Robust LLM Fingerprints Adversarially Robust?cited by 7
  4. 2025LeakyCLIP: Extracting Training Data from CLIPcited by 4
  5. 2025Differential-informed Sample Selection Accelerates Multimodal Contrastive Learningcited by 3
  6. 2024MBSS-T1: Model-Based Subject-Specific Self-Supervised Motion Correction for Robust Cardiac T1 Mappingcited by 2
  7. 2025AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMscited by 1
  8. 2025Localizing and Mitigating Memorization in Image Autoregressive Modelscited by 1
  9. 2025Membership Inference Attacks Beyond Overfittingcited by 1
  10. 2024EMP: Enhance Memory in Data Pruningcited by 0
  11. 2024Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replaycited by 0
  12. 2025Memorizing Long-tail Data Can Help Generalization Through Compositioncited by 0
2 more
  1. 2026Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forwardcited by 0
  2. 2026Similarity-Aware Machine Unlearningcited by 0