Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks
arxiv(2024)
摘要
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 propose a novel debiasing framework, Debiasing Global
Workspace, introducing attention-based information bottlenecks for learning
compositional representations of attributes without defining specific bias
types. Based on our observation that learning shape-centric representation
helps robust performance on OOD datasets, we adopt those abilities to learn
robust and generalizable representations of decomposable latent embeddings
corresponding to intrinsic and biasing attributes. We conduct comprehensive
evaluations on biased datasets, along with both quantitative and qualitative
analyses, to showcase our approach's efficacy in attribute-centric
representation learning and its ability to differentiate between intrinsic and
bias-related features.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要