mlsanityData to 7 Oct 2026

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning

arXiv 2402.11237 ↗First posted 17 Feb 2024cs.LG cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are vulnerable to shortcut learning: rather than learning the intended task, they tend to draw inconclusive relationships between their inputs and outputs. Shortcut learning is ubiquitous among many failure cases of neural networks, and traces of this phenomenon can be seen in their generalizability issues, domain shift, adversarial vulnerability, and even bias towards majority groups. In this paper, we argue that this commonality in the cause of various DNN issues creates a significant opportunity that should be leveraged to find a unified solution for shortcut learning. To this end, we outline the recent advances in topological data analysis (TDA), and persistent homology (PH) in particular, to sketch a unified roadmap for detecting shortcuts in deep learning. We demonstrate our arguments by investigating the topological features of computational graphs in DNNs using two cases of unlearnable examples and bias in decision-making as our test studies. Our analysis of these two failure cases of DNNs reveals that finding a unified solution for shortcut learning in DNNs is not out of reach, and TDA can play a significant role in forming such a framework.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 36 of its 55 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

36 of 55 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  9. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  10. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  11. 2018Recognition in Terra Incognitacited by 655
  12. 2018Deep Visual Domain Adaptation: A Surveycited by 634
24 more
  1. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  2. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  3. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  4. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 338
  5. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  6. 2019Label-Consistent Backdoor Attackscited by 285
  7. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  8. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  9. 2021Adversarial Examples Make Strong Poisonscited by 115
  10. 2021Salient ImageNet: How to discover spurious features in Deep Learning?cited by 114
  11. 2021Backdoor Attack in the Physical Worldcited by 82
  12. 2019Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encodercited by 70
  13. 2021Availability Attacks Create Shortcutscited by 60
  14. 2022Autoregressive Perturbations for Data Poisoningcited by 45
  15. 2021Unsupervised Learning of Debiased Representations with Pseudo-Attributescited by 44
  16. 2021Topological Detection of Trojaned Neural Networkscited by 34
  17. 2023BackdoorBox: A Python Toolbox for Backdoor Learningcited by 25
  18. 2023What Can We Learn from Unlearnable Datasets?cited by 21
  19. 2021Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphscited by 20
  20. 2023The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Modelscited by 19
  21. 2017Adversary Detection in Neural Networks via Persistent Homologycited by 12
  22. 2020Topologically Densified Distributionscited by 6
  23. 2022ConfounderGAN: Protecting Image Data Privacy with Causal Confoundercited by 4
  24. 2022An Adversarial Robustness Perspective on the Topology of Neural Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mechanistic Anomaly Detection via Functional Attributioncited by 1