Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917859776528384 |
|---|---|
| author | Steinmann, David Divo, Felix Kraus, Maurice Wüst, Antonia Struppek, Lukas Friedrich, Felix Kersting, Kristian |
| author_facet | Steinmann, David Divo, Felix Kraus, Maurice Wüst, Antonia Struppek, Lukas Friedrich, Felix Kersting, Kristian |
| contents | Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however, remains fragmented across various terminologies, hindering the progress of the field as a whole. Consequently, we introduce a unifying taxonomy of shortcut learning by providing a formal definition of shortcuts and bridging the diverse terms used in the literature. In doing so, we further establish important connections between shortcuts and related fields, including bias, causality, and security, where parallels exist but are rarely discussed. Our taxonomy organizes existing approaches for shortcut detection and mitigation, providing a comprehensive overview of the current state of the field and revealing underexplored areas and open challenges. Moreover, we compile and classify datasets tailored to study shortcut learning. Altogether, this work provides a holistic perspective to deepen understanding and drive the development of more effective strategies for addressing shortcuts in machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05152 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation Steinmann, David Divo, Felix Kraus, Maurice Wüst, Antonia Struppek, Lukas Friedrich, Felix Kersting, Kristian Machine Learning Artificial Intelligence Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in this area, however, remains fragmented across various terminologies, hindering the progress of the field as a whole. Consequently, we introduce a unifying taxonomy of shortcut learning by providing a formal definition of shortcuts and bridging the diverse terms used in the literature. In doing so, we further establish important connections between shortcuts and related fields, including bias, causality, and security, where parallels exist but are rarely discussed. Our taxonomy organizes existing approaches for shortcut detection and mitigation, providing a comprehensive overview of the current state of the field and revealing underexplored areas and open challenges. Moreover, we compile and classify datasets tailored to study shortcut learning. Altogether, this work provides a holistic perspective to deepen understanding and drive the development of more effective strategies for addressing shortcuts in machine learning. |
| title | Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.05152 |