arXiv Machine Learning
Whitening Improves Robustness to Spurious Correlations in Linear Probes
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 2
Invariance Pair Guidance: Robustness to Spurious Correlations via Corrective Gradients
arXiv:2502. 18975v2 Announce Type: replace Abstract: Machine learning models are inherently bound to the distribution of the training data, often exploiting non-causal shortcuts.
arXiv AI
Jun 2
Shortcut to Nowhere: Demystifying Deep Spurious Regression
arXiv:2606. 01723v1 Announce Type: cross 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.
arXiv AI
Sep 10
SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
The paper introduces Dynamic DAE Guardrails (DSG), a method that uses Dynamic Sparse Autoencoders to perform precision unlearning in large language models. DSG leverages principled feature selection and a dynamic classifier to target activation-based unlearning, outperforming existing gradient‑based methods in terms of computational efficiency, stability, sequential unlearning, resistance to relearning attacks, data efficiency, and interpretability.
arXiv Machine Learning
Jun 3
Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing
arXiv:2606. 02830v1 Announce Type: new Abstract: Real-world datasets often contain spurious correlations that are not causally related to the target label.
arXiv Machine Learning
Sep 23
eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts
The paper introduces eXplaining to Learn (eX2L), an interpretable framework that regularizes a classifier by penalizing similarity between Grad‑CAM maps of the main label classifier and a confounder classifier. This approach decorrelates confounding features from latent representations during training. On the Spawrious Many‑to‑Many Hard Challenge benchmark, eX2L outperforms the current state‑of‑the‑art by 5.49% in average accuracy and 10.90% in worst‑group accuracy, while also demonstrating functional domain invariance through explicit label‑nuisance decoupling.
arXiv AI
Aug 12
Token-Based Detection of Spurious Correlations in Vision Transformers
arXiv:2509. 04009v2 Announce Type: replace-cross Abstract: Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or unintended but statistically relevant signals.