Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks

arXiv:2403.14140v1 Announce Type: cross
Abstract: Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD) generalization. Although many debiasing approaches have been proposed to ensure correct predictions from biased datasets, few studies have considered learning latent embedding consisting of intrinsic and biased attributes that contribute to improved performance and explain how the model pays attention to attributes. In this paper, we …

abstract arxiv bottlenecks capabilities cs.cv cs.lg dataset datasets distribution information labels learn networks neural networks predictions studies type via