Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss

Autor:	Vandenhirtz, Moritz, Manduchi, Laura, Marcinkevičs, Ričards, Vogt, Julia E.
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Presented at the Domain Generalization Workshop (ICLR 2023)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.19671 Zobrazit plný text záznamu View this record from Arxiv