Shortcut to Nowhere: Demystifying Deep Spurious Regression

• URL: http://arxiv.org/abs/2606.01723v1
• Date: Mon, 01 Jun 2026 05:40:11 GMT
• Title: Shortcut to Nowhere: Demystifying Deep Spurious Regression
• Abstract summary: We define Deep Spurious Regression (DSR) as learning from regression data with attribute-label confounding.<n>Motivated by the intrinsic difference between classification and regression shortcuts, we propose to exploit the similarity among spurious attributes in both label and feature spaces.<n>Our work fills the gap in benchmarks and techniques for studying spurious correlations in continuous prediction.
• Score: 4.283376582002132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world regression often exhibits shortcuts: attributes that are spuriously correlated with continuous targets in training, yet unreliable under deployment shifts; regressing targets using such shortcuts may fail catastrophically at test time. Existing studies on spurious correlations focus primarily on classification, where labels are categorical and groups are naturally defined. However, many real-world tasks require continuous prediction, where hard label boundaries or discrete group-label pairs do not exist. We define Deep Spurious Regression (DSR) as learning from regression data with attribute-label confounding, addressing continuous spurious correlations, and generalizing to all attribute-label combinations at test time. Motivated by the intrinsic difference between classification and regression shortcuts, we propose to exploit the similarity among spurious attributes in both label and feature spaces, thereby accounting for nearby targets and related groups while calibrating both label and learned feature distributions across attributes. Extensive experiments on common real-world DSR datasets that span computer vision, environmental sensing, and large language model (LLM) regression verify the superior performance of our strategies. Our work fills the gap in benchmarks and techniques for studying spurious correlations in continuous prediction.

Related papers

• Generative Classifiers Avoid Shortcut Solutions [84.23247217037134]
  Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail under minor distribution shift.<n>We show that generative classifiers can avoid this issue by modeling all features, both core and spurious, instead of mainly spurious ones.<n>We find that diffusion-based and autorerimigressive generative classifiers achieve state-of-the-art performance on five standard image and text distribution shift benchmarks.
  arXiv  Detail & Related papers  (2025-12-31T18:31:46Z)
• Semi-Supervised Regression with Heteroscedastic Pseudo-Labels [50.54050677867914]
  We propose an uncertainty-aware pseudo-labeling framework that dynamically adjusts pseudo-label influence from a bi-level optimization perspective.<n>We provide theoretical insights and extensive experiments to validate our approach across various benchmark SSR datasets.
  arXiv  Detail & Related papers  (2025-10-17T03:06:23Z)
• ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models [26.544938760265136]
  Deep learning models inadvertently learn spurious correlations between targets and non-essential features.<n>In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels.<n>Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space.
  arXiv  Detail & Related papers  (2025-05-20T04:21:17Z)
• Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression [6.649953811669191]
  Deep imbalanced regression (DIR) is an intriguing yet under-explored problem in machine learning.<n>We first bridge the connection between the objectives of DIR and classification from a Bayesian perspective.<n>Specifically, by aggregating the data at nearby labels into the same groups, we introduce an ordinal group-aware contrastive learning loss.<n>We also propose a symmetric descending soft labeling strategy to exploit the intrinsic similarity across the data.
  arXiv  Detail & Related papers  (2024-12-16T19:54:57Z)
• Out of spuriousity: Improving robustness to spurious correlations without group annotations [2.592470112714595]
  We propose an approach to extract a subnetwork from a fully trained network that does not rely on spurious correlations. The increase in the worst-group performance of our approach contributes to strengthening the hypothesis that there exists a subnetwork in a fully trained dense network.
  arXiv  Detail & Related papers  (2024-07-20T20:24:14Z)
• Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation [26.544938760265136]
  Deep neural classifiers rely on spurious correlations between spurious attributes of inputs and targets to make predictions. We propose a self-guided spurious correlation mitigation framework. We show that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori.
  arXiv  Detail & Related papers  (2024-05-06T17:12:21Z)
• Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery [56.172872410834664]
  Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning. We propose a Memory Consistency guided Divide-and-conquer Learning framework (MCDL) Our method outperforms state-of-the-art models by a large margin on both seen and unseen classes of the generic image recognition.
  arXiv  Detail & Related papers  (2024-01-24T09:39:45Z)
• ConR: Contrastive Regularizer for Deep Imbalanced Regression [6.5356646210003015]
  ConR is a contrastive regularizer that models global and local label similarities in feature space. We show that ConR significantly boosts the performance of all the state-of-the-art methods on four large-scale deep imbalanced regression benchmarks.
  arXiv  Detail & Related papers  (2023-09-13T00:30:32Z)
• A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning [111.05365744744437]
  Unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. In this work, we first prove that for contrastive learning, inaccurate label assignment heavily impairs its generalization for semantic instance discrimination. Inspired by this theory, we propose a novel self-labeling refinement approach for contrastive learning.
  arXiv  Detail & Related papers  (2021-06-28T14:24:52Z)
• Delving into Deep Imbalanced Regression [41.90687097747504]
  We define Deep Imbalanced Regression (DIR) as learning from imbalanced data with continuous targets. Motivated by the intrinsic difference between categorical and continuous label space, we propose distribution smoothing for both labels and features. Our work fills the gap in benchmarks and techniques for practical imbalanced regression problems.
  arXiv  Detail & Related papers  (2021-02-18T18:56:03Z)
• ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning [52.831894583501395]
  Continual learning assumes the incoming data are fully labeled, which might not be applicable in real applications. We propose deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN) We show ORDisCo achieves significant performance improvement on various semi-supervised learning benchmark datasets for SSCL.
  arXiv  Detail & Related papers  (2021-01-02T09:04:14Z)
• Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification [64.37745443119942]
  This paper jointly enforces visual and temporal consistency in the combination of a local one-hot classification and a global multi-class classification. Experimental results on three large-scale ReID datasets demonstrate the superiority of proposed method in both unsupervised and unsupervised domain adaptive ReID tasks.
  arXiv  Detail & Related papers  (2020-07-21T14:31:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.