Spurious Correlation Robustness

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 45

All topics

Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
May 19, 2026Nikhil Cherian Kurian, Victor Caquilpan Parra, Abin Shoby +2Distribution Shift Robustness Algorithmic Bias
Australian Institute for Machine Learning, Adelaide University, Adelaide, Australia
Shortcut Mitigation via Spurious-Positive Samples
May 13, 2026Phuong Quynh Le, Jörg Schlötterer, Sari Sadiya +2Neural Network Robustness Spurious Correlation Robustness
University of Marburg · Goethe University Frankfurt
Separating Shortcut Transition from Cross-Family OOD Failure in a Minimal Model
May 13, 2026Hongmin LiLogistic Regression OOD Generalization
School of Life Science and Technology, Institute of Science Tokyo · Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo
Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations
May 12, 2026Shufan Ming, Joe D. Menke, Neil R. Smalheiser +1Adversarial Training Distribution Shift Robustness
School of Information Sciences University of Illinois Urbana-Champaign Champaign, USA · Department of Psychiatry University of Illinois Chicago Chicago, USA
Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training
May 11, 2026Christian Moya, Alex Semendinger, Guang Lin +1Pairwise Preference Learning LLM Alignment
Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs
May 11, 2026Youssef Zaazou, Mark ThomasVLM Robustness Vision-Language Models
Independent Researcher
What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
May 8, 2026Fan Zhang, Shiming Fan, Hua WangMultivariate Time Series Forecasting Feature Interaction Modeling
Shandong Technology and Business University, Yantai, Shandong, China · Ludong University, Yantai, Shandong, China
eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts
May 7, 2026Paulo Mario P. Medina, Jose Marie Antonio Miñoza, Sebastian C. IbañezDistribution Shift Robustness Interpretable ML
Center for AI Research
When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data
May 6, 2026Miguel Fernandez-de-Retana, Ruben Sanchez-Corcuera, Unai Zulaika +2Causal Discovery Gene Regulatory Network Inference
Faculty of Engineering University of Deusto Bilbao, Spain
When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift
May 4, 2026Zhecheng Sheng, Yongsen Tan, Xiruo Ding +2Distribution Shift Robustness Prompt Tuning
University of Minnesota · University of Washington · 3Stanford University
Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification
May 4, 2026Shubham Harkare, Arvind Yogesh Suresh Babu, Yash KulkarniGradient-Based Attribution Sentiment Analysis
University of Michigan
A Toolkit for Detecting Spurious Correlations in Speech Datasets
Apr 29, 2026Lara Gauder, Pablo Riera, Andrea Slachevsky +3Speech Processing Spurious Correlation Robustness
Instituto de Investigaci´on en Ciencias de la Computaci´on, UBA-CONICET, Argentina · Departamento de Computaci´on, Facultad de Ciencias Exactas y Naturales, UBA, Argentina · Facultad de Medicina, Universidad de Chile, Chile +1
Invariance Pair Guidance: Robustness to Spurious Correlations via Corrective Gradients
Feb 26, 2025Martin Surner, Abdelmajid Khelil, Ludwig BothmannSpurious Correlation Robustness Invariant Representation Learning
Institute for Data and Process Science, Landshut University of Applied Sciences, Landshut, Germany. · Computer Science Department, Landshut University of Applied Sciences, Landshut, Germany. · Department of Statistics, LMU Munich, Munich, Germany. +1
When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
Date pendingShaowen Wang, Yiqi Dong, Ruinian Chang +4Hallucination in Language Models LLM Hallucination Detection
Institute for Interdisciplinary Information Sciences, Tsinghua University
TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
Date pendingZe Chen, Qiming Yu, Zijia Song +2Memory-Augmented Neural Networks Disentangled Representation Learning
National University of Defense Technology Hefei, Anhui, China

May 19, 2026, cs.CVJ/K move · Enter open · S save

Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation

Nikhil Cherian Kurian, Victor Caquilpan Parra, Abin Shoby, Luke Whitbread+1

Australian Institute for Machine Learning, Adelaide University, Adelaide, Australia

Distribution Shift Robustness Algorithmic Bias Medical Image Classification Spurious Correlation Robustness

Open paper AskPDF arXiv

Age dependent performance disparities in medical image classification often arise because age acts as a confounder, linking imaging morphology with disease prevalence. In practice, disparities can manifest as overdiagnosis at ages where disease prevalence is higher and underdiagnosis at ages where prevalence is lower, and can worsen under train test shifts in the age distribution. Conventional mitigation approaches that enforce strict age invariance may suppress diagnostically meaningful information encoded in age. We therefore propose a robust framework that mitigates the effects of age-dependent confounding by targeting spurious age linked trends rather than enforcing invariance. Following a warm-up phase, we characterize sample difficulty and model its age-dependent trends in a label-conditioned manner. We decorrelate age from dominant age difficulty trends using robust, Huber weighted affinity weights, attenuating confounding-driven shortcuts while preserving clinically meaningful, nonlinear age information. We further introduce an Age Coverage Score that scales the decorrelation penalty by minibatch age variance to ensure stable optimization under limited age diversity. Across two radiology datasets, our approach reduces age dependent true and false positive disparities with minimal AUC impact and remains robust to increasing train test age distribution shifts.

Momentum

Related topics

Latest papers 45