# Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More

arXiv: https://arxiv.org/abs/2602.03066 · HTML: https://mlsanity.com/paper/2602.03066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent](https://mlsanity.com/paper/1902.06720/) (2019)
- [On Lazy Training in Differentiable Programming](https://mlsanity.com/paper/1812.07956/) (2018)
- [The Implicit Bias of Gradient Descent on Separable Data](https://mlsanity.com/paper/1710.10345/) (2017)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [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)
- [Towards Understanding the Spectral Bias of Deep Learning](https://mlsanity.com/paper/1912.01198/) (2019)
- [The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies](https://mlsanity.com/paper/1906.00425/) (2019)
- [Neural Networks as Kernel Learners: The Silent Alignment Effect](https://mlsanity.com/paper/2111.00034/) (2021)
- [Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks](https://mlsanity.com/paper/2205.09653/) (2022)
- [A Fine-Grained Spectral Perspective on Neural Networks](https://mlsanity.com/paper/1907.10599/) (2019)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [On the Foundations of Shortcut Learning](https://mlsanity.com/paper/2310.16228/) (2023)
- [Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias](https://mlsanity.com/paper/2305.18761/) (2023)
- [Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations](https://mlsanity.com/paper/2107.00520/) (2021)
- [Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy](https://mlsanity.com/paper/2308.12553/) (2023)
- [A Theory of Neural Tangent Kernel Alignment and Its Influence on Training](https://mlsanity.com/paper/2105.14301/) (2021)
- [What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?](https://mlsanity.com/paper/2210.05577/) (2022)
- [Revisiting the Importance of Amplifying Bias for Debiasing](https://mlsanity.com/paper/2205.14594/) (2022)
- [Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse](https://mlsanity.com/paper/2405.05587/) (2024)

## Abstract (arXiv)

One of the chronic problems of deep-learning models is shortcut learning. In a case where the majority of training data are dominated by a certain feature, neural networks prefer to learn such a feature even if the feature is not generalizable outside the training set. Based on the framework of Neural Tangent Kernel (NTK), we analyzed the case of linear neural networks to derive some important properties of shortcut learning. We defined a feature of a neural network as an eigenfunction of NTK. Then, we found that shortcut features correspond to features with larger eigenvalues when the shortcuts stem from the imbalanced number of samples in the clustered distribution. We also showed that the features with larger eigenvalues still have a large influence on the neural network output even after training, due to data variances in the clusters. Such a preference for certain features remains even when a margin of a neural network output is controlled, which shows that the max-margin bias is not the only major reason for shortcut learning. These properties of linear neural networks are empirically extended for more complex neural networks as a two-layer fully-connected ReLU network and a ResNet-18.