paper-with-me

Papers

Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective

2024-11-01 · Yuqing Zhou, Ziwei Zhu

In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when faced with out-of-distribution data where such spurious correlations no longer hold. To address this challenge, we propose the Causally Calibrated Robust Classifier (CCR), which aims to reduce models' reliance on spurious correlations and improve model robustness. Our approach integrates a causal feature selection method based on counterfactual reasoning, along with an unbiased inverse propensity weighting (IPW) loss function. By focusing on selecting causal features, we ensure that the model relies less on spurious features during prediction. We theoretically justify our approach and empirically show that CCR achieves state-of-the-art performance among methods without group labels, and in some cases, it can compete with the models that utilize group labels.

📄 PDF Abstract BibTeX arXiv:2411.01045

Code (1)

yuqing-zhou/causal-learning-for-robust-classifier 공식 구현 pytorch

Tasks

counterfactualCounterfactual Reasoningfeature selectiontext-classificationText Classification

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis

2025-11-28 · Louisa Fay, Hajer Reguigui, Bin Yang, Sergios Gatidis 외 arxiv

Deep learning models can excel on medical tasks, yet often experience spurious correlations, known as shortcut learning, leading to poor generalization in new environments. Particularly in medical imaging, where multiple…

Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention

2025-11-13 · Zhe Xu, Zhicai Wang, Junkang Wu, Jinda Lu 외 arxiv

Large Vision-Language Models (LVLMs) often suffer from object hallucination, making erroneous judgments about the presence of objects in images. We propose this primar- ily stems from spurious correlations arising when m…

Object Recognition

Towards Robust Classification Model by Counterfactual and Invariant Data Generation

2021-06-02 · CVPR 2021 1 · Chun-Hao Chang, George Alexandru Adam, Anna Goldenberg

Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occu…

Classificationcounterfactualimage-classificationImage Classification+2

Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning

2024-04-22 · Kang Luo, Yuanshao Zhu, Wei Chen, Kun Wang 외

Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial co…

Representation LearningTrajectory Modeling

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

2025-08-06 · Peizheng Guo, Jingyao Wang, Wenwen Qiang, Jiahuan Zhou 외 arxiv

Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionately to task-irrelevant background regions …