paper-with-me

Papers

Unsupervised Concept Discovery Mitigates Spurious Correlations

2024-02-20 · Md Rifat Arefin, Yan Zhang, Aristide Baratin, Francesco Locatello, Irina Rish, Dianbo Liu, Kenji Kawaguchi

Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relying on prior knowledge and group annotation to remove spurious correlations, which may not be readily available in many applications. In this paper, we establish a novel connection between unsupervised object-centric learning and mitigation of spurious correlations. Instead of directly inferring subgroups with varying correlations with labels, our approach focuses on discovering concepts: discrete ideas that are shared across input samples. Leveraging existing object-centric representation learning, we introduce CoBalT: a concept balancing technique that effectively mitigates spurious correlations without requiring human labeling of subgroups. Evaluation across the benchmark datasets for sub-population shifts demonstrate superior or competitive performance compared state-of-the-art baselines, without the need for group annotation. Code is available at https://github.com/rarefin/CoBalT.

📄 PDF Abstract BibTeX arXiv:2402.13368

Code (1)

rarefin/cobalt 공식 구현

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models

2024-11-06 · Maya Varma, Jean-Benoit Delbrouck, Zhihong Chen, Akshay Chaudhari 외

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spu…

image-classificationImage Classificationzero-shot-classificationZero-Shot Learning

Sparse Causal Discovery with Generative Intervention for Unsupervised Graph Domain Adaptation

2025-07-10 · Junyu Luo, Yuhao Tang, Yiwei Fu, Xiao Luo 외 arxiv

Unsupervised Graph Domain Adaptation (UGDA) leverages labeled source domain graphs to achieve effective performance in unlabeled target domains despite distribution shifts. However, existing methods often yield suboptima…

GRAPH DOMAIN ADAPTATION

Debiasing Reward Models by Representation Learning with Guarantees

2025-10-27 · Ignavier Ng, Patrick Blöbaum, Siddharth Bhandari, Kun Zhang 외 arxiv

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these…

Representation LearningReinforcement Learning

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…

A Causal Perspective of Stock Prediction Models

2025-03-26 · Songci Xu, Qiangqiang Cheng, Chi-Guhn Lee

In the realm of stock prediction, machine learning models encounter considerable obstacles due to the inherent low signal-to-noise ratio and the nonstationary nature of financial markets. These challenges often result in…

Causal DiscoveryDomain GeneralizationEconometricsPrediction+2