# The Pitfalls of Memorization: When Memorization Hurts Generalization

arXiv: https://arxiv.org/abs/2412.07684 · HTML: https://mlsanity.com/paper/2412.07684/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 74 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 30 of 62)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [The Implicit Bias of Gradient Descent on Separable Data](https://mlsanity.com/paper/1710.10345/) (2017)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Benign Overfitting in Linear Regression](https://mlsanity.com/paper/1906.11300/) (2019)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Improving Out-of-Distribution Robustness via Selective Augmentation](https://mlsanity.com/paper/2201.00299/) (2022)

## Built on by (most cited first, 19 of 19)

- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges](https://mlsanity.com/paper/2502.01612/) (2025)
- [Dataset distillation for memorized data: Soft labels can leak held-out teacher knowledge](https://mlsanity.com/paper/2506.14457/) (2025)
- [Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs](https://mlsanity.com/paper/2510.02833/) (2025)
- [Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting](https://mlsanity.com/paper/2503.02296/) (2025)
- [Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs](https://mlsanity.com/paper/2507.21914/) (2025)
- [Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks](https://mlsanity.com/paper/2506.01820/) (2025)
- [Generalization or Memorization: Dynamic Decoding for Mode Steering](https://mlsanity.com/paper/2510.22099/) (2025)
- [Mitigating Memorization Where It Happens](https://mlsanity.com/paper/2602.08901/) (2026)
- [Memorization in Graph Neural Networks](https://mlsanity.com/paper/2508.19352/) (2025)
- [Proteus: Incremental Memory Activation for Long-Context Sequence Modeling](https://mlsanity.com/paper/2608.16844/) (2026)
- [Anatomy of a failure: When, how, and why deep vision fails in scientific domains](https://mlsanity.com/paper/2605.04231/) (2026)
- [Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations](https://mlsanity.com/paper/2605.20771/) (2026)
- [Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing](https://mlsanity.com/paper/2606.02830/) (2026)
- [Random Label Prediction Heads for Studying Memorization in Deep Neural Networks](https://mlsanity.com/paper/2607.11541/) (2026)
- [What do Reward Models Memorize?](https://mlsanity.com/paper/2607.24484/) (2026)
- [Whitening Improves Robustness to Spurious Correlations in Linear Probes](https://mlsanity.com/paper/2609.39177/) (2026)
- [You May Be Running the Wrong Inception Crop](https://mlsanity.com/paper/2610.04147/) (2026)
- [Statistical Vignettes on the Grokking Phenomenon](https://mlsanity.com/paper/2610.18811/) (2026)

## Abstract (arXiv)

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations.This behavior leads to poor generalization when the learned explanations rely on spurious correlations. In this work, we formalize the interplay between memorization and generalization, showing that spurious correlations would particularly lead to poor generalization when are combined with memorization. Memorization can reduce training loss to zero, leaving no incentive to learn robust, generalizable patterns. To address this, we propose memorization-aware training (MAT), which uses held-out predictions as a signal of memorization to shift a model's logits. MAT encourages learning robust patterns invariant across distributions, improving generalization under distribution shifts.