ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models Article Swipe

MAKE IMPACT

Guangtao Zheng , Wenqian Ye , Aidong Zhang · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.13910

Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously correlates with it. This prediction behavior, known as spurious bias, severely degrades model performance on data that lacks the learned spurious correlations. Existing methods on spurious bias mitigation typically require a variety of data groups with spurious correlation annotations called group labels. However, group labels require costly human annotations and often fail to capture subtle spurious biases such as relying on specific pixels for predictions. In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels. Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space. The model is then retrained to be invariant to the identified prediction shortcuts for improved robustness. We theoretically analyze the effectiveness of the framework and empirically demonstrate that it is an efficient and practical tool for improving a model's robustness to spurious bias on diverse datasets.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2505.13910

PDF

https://arxiv.org/pdf/2505.13910

OA Status

green

OpenAlex ID

https://openalex.org/W4415332727

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4415332727

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2505.13910

Digital Object Identifier

Title

ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-05-20

Full publication date if available

Authors

Guangtao Zheng, Wenqian Ye, Aidong Zhang

List of authors in order

Landing page

https://arxiv.org/abs/2505.13910

Publisher landing page

PDF URL

https://arxiv.org/pdf/2505.13910

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2505.13910

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload