Understanding Rare Spurious Correlations in Neural NetworksDownload PDF

Published: 21 Jul 2022, Last Modified: 28 May 2023SCIS 2022 PosterReaders: Everyone
Keywords: rare spurious correlation, privacy
TL;DR: Rare spurious correlations appear in neural networks even when the number of spurious samples is small.
Abstract: Neural networks are known to use spurious correlations such as background information for classification. While prior work has looked at spurious correlations that are widespread in the training data, in this work, we investigate how sensitive neural networks are to rare spurious correlations, which may be harder to detect and correct, and may lead to privacy leaks. We introduce spurious patterns correlated with a fixed class to a few training examples and find that it takes only a handful of such examples for the network to learn the correlation. Furthermore, these rare spurious correlations also impact accuracy and privacy. We empirically and theoretically analyze different factors involved in rare spurious correlations and propose mitigation methods accordingly. Specifically, we observe that $\ell_2$ regularization and adding Gaussian noise to inputs can reduce the undesirable effects.
Confirmation: Yes
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2202.05189/code)
0 Replies