Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples

• URL: http://arxiv.org/abs/2608.05419v1
• Date: Wed, 05 Aug 2026 21:29:11 GMT
• Title: Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples
• Abstract summary: Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold.<n>We show that a usable signal is available after convergence, when loss no longer distinguishes the two populations.<n>Using the detected samples to rebalance training raises worst-group accuracy on Waterbirds from 57.3% to 80.8%, against 85.8% with ground-truth group labels.
• Score: 2.036610981667781
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold. Existing methods for identifying the affected samples without group annotations rely on signals from early training, which requires locating the epoch at which to intervene, a hyperparameter typically selected using group-labeled validation data. We show that a usable signal is available after convergence, when loss no longer distinguishes the two populations. Samples consistent with the spurious correlation are classified by a shared rule, while the remaining samples are fit through configurations specific to individual inputs and are correspondingly more fragile. Applying a fixed perturbation to a converged model's inputs flips the predictions of the latter far more often than the former. The resulting procedure requires two forward passes per training sample, no group annotations at any stage, and no early-stopping epoch. Using the detected samples to rebalance training raises worst-group accuracy on Waterbirds from 57.3% to 80.8%, against 85.8% with ground-truth group labels.

Related papers

• Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents [1.4915002678801434]
  We show that Bonferroni allocation is distribution-free but conservative under correlated errors.<n> coarse-to-fine label selection can create near-perfect measured correlation without learned dependence.<n>A modular certificate using per-stage certificates and a pairwise overlap bound yields a positive average gain of 0.6%.
  arXiv  Detail & Related papers  (2026-08-04T23:48:36Z)
• Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing [8.645414910735449]
  We develop a two-stage sample scoring function that disentangles the learning dynamics of core and spurious features.<n>Based on our proposed metric, we introduce a new algorithm to find and prioritize informative samples both with and without spurious correlations.
  arXiv  Detail & Related papers  (2026-06-01T19:48:20Z)
• Active Data Sampling and Generation for Bias Remediation [0.0]
  A mixed active sampling and data generation strategy -- called samplation -- is proposed to compensate during fine-tuning of a pre-trained classifer the unfair classifications it produces.<n>Using as case study Deep Models for visual semantic role labeling, the proposed method has been able to fully cure a simulated gender bias starting from a 90/10 imbalance.
  arXiv  Detail & Related papers  (2025-03-26T10:42:15Z)
• Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation [3.894771553698554]
  Empirical Risk Minimization (ERM) models tend to rely on attributes that have high spurious correlation with the target. This can degrade the performance on underrepresented (or'minority') groups that lack these attributes. We propose Environment-based Validation and Loss-based Sampling (EVaLS) to enhance robustness to spurious correlation.
  arXiv  Detail & Related papers  (2024-10-07T08:17:44Z)
• Bias Amplification Enhances Minority Group Performance [10.380812738348899]
  We propose BAM, a novel two-stage training algorithm. In the first stage, the model is trained using a bias amplification scheme via introducing a learnable auxiliary variable for each training sample. In the second stage, we upweight the samples that the bias-amplified model misclassifies, and then continue training the same model on the reweighted dataset.
  arXiv  Detail & Related papers  (2023-09-13T04:40:08Z)
• Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling [77.15766509677348]
  Conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to another latent attribute. We propose a general two-step strategy to mitigate this issue.
  arXiv  Detail & Related papers  (2022-12-05T08:09:33Z)
• Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection [81.07346419422605]
  Anomaly detection aims at identifying deviant samples from the normal data distribution. Contrastive learning has provided a successful way to sample representation that enables effective discrimination on anomalies. We propose a novel hierarchical semi-supervised contrastive learning framework, for contamination-resistant anomaly detection.
  arXiv  Detail & Related papers  (2022-07-24T18:49:26Z)
• An analysis of over-sampling labeled data in semi-supervised learning with FixMatch [66.34968300128631]
  Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. We compare it to an alternative setting where each mini-batch is uniformly sampled from all the training data, labeled or not.
  arXiv  Detail & Related papers  (2022-01-03T12:22:26Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations [98.3066727301239]
  We identify two key properties of the training data that drive this behavior. We show how the inductive bias of models towards "memorizing" fewer examples can cause over parameterization to hurt.
  arXiv  Detail & Related papers  (2020-05-09T01:59:13Z)

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.