Can I read Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes on EtoBox?

Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes by Kumar, Abhinav; Deshpande, Amit; Sharma, Amit is a scholarly article available to read on EtoBox.

What is Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes about?

In many classification datasets, the task labels are spuriously correlated with some input attributes. Classifiers trained on such datasets often rely on these attributes for prediction, especially when the spurious correlation is high, and thus fail to generalize whenever there is a shift in the attributes' correlation at deployment. If we assume that the spurious attributes are known a priori, several methods have been proposed to learn a classifier that is invariant to the specified attributes. However, in real-world data, information about spurious attributes is typically unavailable. Therefore, we propose a method to automatically identify spurious attributes by estimating their causal effect on the label and then use a regularization objective to mitigate the classifier's reliance on them. Compared to a recent method for identifying spurious attributes, we find that our method is more accurate in removing the attribute from the learned model, especially when spurious correlation is high. Specifically, across synthetic, semi-synthetic, and real-world datasets, our method shows significant improvement in a metric used to quantify the dependence of a classifier on spurious attri

Author

Kumar, Abhinav; Deshpande, Amit; Sharma, Amit

Published

2023

Language

EN