Spurious Correlations in Machine Learning: A Survey

arXiv:2402.12715v1 Announce Type: new
Abstract: Machine learning systems are known to be sensitive to spurious correlations between biased features of the inputs (e.g., background, texture, and secondary objects) and the corresponding labels. These features and their correlations with the labels are known as "spurious" because they tend to change with shifts in real-world data distributions, which can negatively impact the model's generalization and robustness. In this survey, we provide a comprehensive review of this issue, along with a taxonomy of …

abstract arxiv change correlations cs.lg features inputs labels learning systems machine machine learning objects survey systems texture type world