Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
This work addresses the challenge of model generalization and robustness for the ML/AI community by providing a comprehensive overview, but it is incremental as it synthesizes existing knowledge rather than proposing new methods.
The paper tackles the fragmented research on shortcuts (e.g., spurious correlations) in machine learning by introducing a unifying taxonomy and formal definition, bridging diverse terminologies and connecting to related fields like bias and causality.
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.