An XAI-based Analysis of Shortcut Learning in Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915253292367872 |
|---|---|
| author | Le, Phuong Quynh Schlötterer, Jörg Seifert, Christin |
| author_facet | Le, Phuong Quynh Schlötterer, Jörg Seifert, Christin |
| contents | Machine learning models tend to learn spurious features - features that strongly correlate with target labels but are not causal. Existing approaches to mitigate models' dependence on spurious features work in some cases, but fail in others. In this paper, we systematically analyze how and where neural networks encode spurious correlations. We introduce the neuron spurious score, an XAI-based diagnostic measure to quantify a neuron's dependence on spurious features. We analyze both convolutional neural networks (CNNs) and vision transformers (ViTs) using architecture-specific methods. Our results show that spurious features are partially disentangled, but the degree of disentanglement varies across model architectures. Furthermore, we find that the assumptions behind existing mitigation methods are incomplete. Our results lay the groundwork for the development of novel methods to mitigate spurious correlations and make AI models safer to use in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15664 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An XAI-based Analysis of Shortcut Learning in Neural Networks Le, Phuong Quynh Schlötterer, Jörg Seifert, Christin Machine Learning Computer Vision and Pattern Recognition Machine learning models tend to learn spurious features - features that strongly correlate with target labels but are not causal. Existing approaches to mitigate models' dependence on spurious features work in some cases, but fail in others. In this paper, we systematically analyze how and where neural networks encode spurious correlations. We introduce the neuron spurious score, an XAI-based diagnostic measure to quantify a neuron's dependence on spurious features. We analyze both convolutional neural networks (CNNs) and vision transformers (ViTs) using architecture-specific methods. Our results show that spurious features are partially disentangled, but the degree of disentanglement varies across model architectures. Furthermore, we find that the assumptions behind existing mitigation methods are incomplete. Our results lay the groundwork for the development of novel methods to mitigate spurious correlations and make AI models safer to use in practice. |
| title | An XAI-based Analysis of Shortcut Learning in Neural Networks |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.15664 |