Open access
Date
2023-05-04Type
- Other Conference Item
ETH Bibliography
yes
Altmetrics
Abstract
Spurious correlations are everywhere. While humans often do not perceive them, neural networks are notorious for learning unwanted associations, also known as biases, instead of the underlying decision rule. As a result, practitioners are often unaware of the biased decision-making of their classifiers. Such a biased model based on spurious correlations might not generalize to unobserved data, leading to unintended, adverse consequences. We propose Signal is Harder (SiH), a variational-autoencoder-based method that simultaneously trains a biased and unbiased classifier using a novel, disentangling reweighting scheme inspired by the focal loss. Using the unbiased classifier, SiH matches or improves upon the performance of state-of-the-art debiasing methods. To improve the interpretability of our technique, we propose a perturbation scheme in the latent space for visualizing the bias that helps practitioners become aware of the sources of spurious correlations. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000614628Publication status
publishedEvent
Subject
Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); FOS: Computer and information sciencesOrganisational unit
09670 - Vogt, Julia / Vogt, Julia
Related publications and datasets
Is identical to: https://doi.org/10.48550/ARXIV.2305.19671
Notes
Spotlight Presentation (Workshop: What do we need for successful domain generalization?)More
Show all metadata
ETH Bibliography
yes
Altmetrics