Shortcut Detection with Variational Autoencoders
Keywords: shortcut detection, shortcuts, machine learning shortcuts, spurious correlations, variational autoencoder, VAE, computer vision, explainable AI
TL;DR: We introduce a VAE-based method to discover spurious correlations in image and audio datasets with minimal human supervision.
Abstract: For real-world applications of machine learning (ML), it is essential that models make predictions based on well-generalizing features rather than spurious correlations in the data. The identification of such spurious correlations, also known as shortcuts, is a challenging problem and has so far been scarcely addressed. In this work, we present a novel approach to detect shortcuts in image and audio datasets by leveraging variational autoencoders (VAEs). The disentanglement of features in the latent space of VAEs allows us to discover feature-target correlations in datasets and semi-automatically evaluate them for ML shortcuts. We demonstrate the applicability of our method on several real-world datasets and identify shortcuts that have not been discovered before.
Submission Number: 15
Loading