paper-with-me

홈 › Papers

Spurious Correlations and Where to Find Them

2023-08-21 · Gautam Sreekumar, Vishnu Naresh Boddeti

Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning. Although there are several algorithms proposed to mitigate it, we are yet to jointly derive the indicators of spurious correlations. As a result, the solutions built upon standalone hypotheses fail to beat simple ERM baselines. We collect some of the commonly studied hypotheses behind the occurrence of spurious correlations and investigate their influence on standard ERM baselines using synthetic datasets generated from causal graphs. Subsequently, we observe patterns connecting these hypotheses and model design choices.

📄 PDF Abstract BibTeX arXiv:2308.11043

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

fail 설명 없음

Similar Papers 제목 키워드 기반

Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding

2025-09-04 · Solha Kang, Esla Timothy Anzaku, Wesley De Neve, Arnout Van Messem 외 arxiv

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 b…

Spuriousness-Aware Meta-Learning for Learning Robust Classifiers

2024-06-15 · Guangtao Zheng, Wenqian Ye, Aidong Zhang

Spurious correlations are brittle associations between certain attributes of inputs and target variables, such as the correlation between an image background and an object class. Deep image classifiers often leverage the…

AttributeLanguage ModellingMeta-Learning

AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization

2022-12-02 · Bhargavi Paranjape, Pradeep Dasigi, Vivek Srikumar, Luke Zettlemoyer 외

Models trained via empirical risk minimization (ERM) are known to rely on spurious correlations between labels and task-independent input features, resulting in poor generalization to distributional shifts. Group distrib…

QQP

Seeing What's Not There: Spurious Correlation in Multimodal LLMs

2025-03-11 · Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian 외

Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we inv…

HallucinationObjectObject HallucinationObject Recognition

Resolving Spurious Correlations in Causal Models of Environments via Interventions

2020-02-12 · Sergei Volodin, Nevan Wichers, Jeremy Nixon

Causal models bring many benefits to decision-making systems (or agents) by making them interpretable, sample-efficient, and robust to changes in the input distribution. However, spurious correlations can lead to wrong c…

Decision Making