Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them

• URL: http://arxiv.org/abs/2604.04518v1
• Date: Mon, 06 Apr 2026 08:29:33 GMT
• Title: Reproducibility study on how to find Spurious Correlations, Shortcut Learning, Clever Hans or Group-Distributional non-robustness and how to fix them
• Abstract summary: We evaluate proposed correction methods based on explainable artificial intelligence (XAI) techniques alongside popular non-XAI baselines.<n>Findings show that XAI-based methods generally outperform non-XAI approaches.<n>Experiments also reveal that the practical application of many methods is hindered by a dependency on group labels.
• Score: 0.8594140167290097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is terminologically fractured across communities that pursue the same goal of ensuring models rely on causally relevant features rather than confounding signals. While frameworks such as distributionally robust optimization (DRO), invariant risk minimization (IRM), shortcut learning, simplicity bias, and the Clever Hans effect all address model failure due to spurious correlations, researchers typically only reference work within their own domains. This reproducibility study unifies these perspectives through a comparative analysis of correction methods under challenging constraints like limited data availability and severe subgroup imbalance. We evaluate recently proposed correction methods based on explainable artificial intelligence (XAI) techniques alongside popular non-XAI baselines using both synthetic and real-world datasets. Findings show that XAI-based methods generally outperform non-XAI approaches, with Counterfactual Knowledge Distillation (CFKD) proving most consistently effective at improving generalization. Our experiments also reveal that the practical application of many methods is hindered by a dependency on group labels, as manual annotation is often infeasible and automated tools like Spectral Relevance Analysis (SpRAy) struggle with complex features and severe imbalance. Furthermore, the scarcity of minority group samples in validation sets renders model selection and hyperparameter tuning unreliable, posing a significant obstacle to the deployment of robust and trustworthy models in safety-critical areas.

Related papers

• FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning [5.979900839748232]
  This paper proposes a framework for efficient collaboration of large models on the edge.<n>FedOPAL adapts the visual prompts as feature prompts, actively correcting the feature distribution of heterogeneous data to a linearly separable space.<n> Experimental results show that FedOPAL not only significantly outperforms the original analytical methods on several benchmarks, but also achieves accuracy comparable to state-of-the-art iterative methods while maintaining zero server-side training costs.
  arXiv  Detail & Related papers  (2026-07-09T11:28:31Z)
• Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting [95.24017293537025]
  Causal Ensemble Agent (CEA) is a novel framework that aggregates structural insights from statistical discovery experts across different graph levels.<n>CEA achieves the strongest overall performance across a wide range of causal discovery methods.
  arXiv  Detail & Related papers  (2026-06-09T09:09:07Z)
• Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation [61.248535801314375]
  Subset-Selected Counterfactual Augmentation (SS-CA)<n>We develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions.<n>Experiments show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks.
  arXiv  Detail & Related papers  (2025-11-15T08:39:22Z)
• MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP [3.9566483499208633]
  This study introduces the Approach of Passive Measures among Educands (APME), a reinforcement learning-based Multi-Armed Bandit (MAB) framework.<n>By leveraging the inverse coefficient of variation as a risk-adjusted metric, the model provides an explainable and scalable mechanism for adaptive assessment.
  arXiv  Detail & Related papers  (2025-08-26T13:23:31Z)
• Statistical Analysis of Conditional Group Distributionally Robust Optimization with Cross-Entropy Loss [16.1456465253627]
  We study multi-source unsupervised domain adaptation, where labeled data are available from multiple source domains and only unlabeled data are observed from the target domain.<n>We propose a novel Group Distributionally Conditional Optimization framework that learns a classifier by minimizing the worst-case cross-entropy loss over the convex combinations of the conditional outcome distributions from sources domains.<n>We establish fast statistical convergence rates for the empirical CG-DRO estimator by constructing two surrogate minimax optimization problems that serve as theoretical bridges.
  arXiv  Detail & Related papers  (2025-07-14T04:21:23Z)
• Robust Molecular Property Prediction via Densifying Scarce Labeled Data [53.24886143129006]
  In drug discovery, compounds most critical for advancing research often lie beyond the training set.<n>We propose a novel bilevel optimization approach that leverages unlabeled data to interpolate between in-distribution (ID) and out-of-distribution (OOD) data.
  arXiv  Detail & Related papers  (2025-06-13T15:27:40Z)
• Improving Group Robustness on Spurious Correlation via Evidential Alignment [26.544938760265136]
  Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets.<n>Existing methods typically mitigate this issue by using external group annotations or auxiliary deterministic models.<n>We propose Evidential Alignment, a novel framework that leverages uncertainty quantification to understand the behavior of the biased models.
  arXiv  Detail & Related papers  (2025-06-12T22:47:21Z)
• Group Robust Classification Without Any Group Information [5.053622900542495]
  This study contends that current bias-unsupervised approaches to group robustness continue to rely on group information to achieve optimal performance. bias labels are still crucial for effective model selection, restricting the practicality of these methods in real-world scenarios. We propose a revised methodology for training and validating debiased models in an entirely bias-unsupervised manner.
  arXiv  Detail & Related papers  (2023-10-28T01:29:18Z)
• REX: Rapid Exploration and eXploitation for AI Agents [103.68453326880456]
  We propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance.
  arXiv  Detail & Related papers  (2023-07-18T04:26:33Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)

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.