English
Related papers

Related papers: Single-weight Model Editing for Post-hoc Spurious …

200 papers

Machine learning models often rely on simple spurious features -- patterns in training data that correlate with targets but are not causally related to them, like image backgrounds in foreground classification. This reliance typically leads…

Machine Learning · Computer Science 2025-06-06 Chenyu You , Haocheng Dai , Yifei Min , Jasjeet S. Sekhon , Sarang Joshi , James S. Duncan

We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model training, our method better utilizes the data one already has by…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Mazda Moayeri , Wenxiao Wang , Sahil Singla , Soheil Feizi

Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In…

Machine Learning · Computer Science 2024-03-08 Yu Yang , Eric Gan , Gintare Karolina Dziugaite , Baharan Mirzasoleiman

A major challenge to out-of-distribution generalization is reliance on spurious features -- patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for…

Machine Learning · Computer Science 2023-06-21 Shikai Qiu , Andres Potapczynski , Pavel Izmailov , Andrew Gordon Wilson

Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting spurious correlations, or…

Computation and Language · Computer Science 2022-05-26 Tianlu Wang , Rohit Sridhar , Diyi Yang , Xuezhi Wang

Often machine learning models tend to automatically learn associations present in the training data without questioning their validity or appropriateness. This undesirable property is the root cause of the manifestation of spurious…

Machine Learning · Computer Science 2023-11-17 Preetam Prabhu Srikar Dammu , Chirag Shah

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Aryan Yazdan Parast , Khawar Islam , Soyoun Won , Basim Azam , Naveed Akhtar

Deep neural networks have been shown to learn and rely on spurious correlations present in the data that they are trained on. Reliance on such correlations can cause these networks to malfunction when deployed in the real world, where these…

Machine Learning · Computer Science 2025-05-20 Varun Mulchandani , Jung-Eun Kim

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

Machine Learning · Computer Science 2022-10-21 Pavel Izmailov , Polina Kirichenko , Nate Gruver , Andrew Gordon Wilson

Neural networks are known to use spurious correlations such as background information for classification. While prior work has looked at spurious correlations that are widespread in the training data, in this work, we investigate how…

Machine Learning · Computer Science 2022-10-06 Yao-Yuan Yang , Chi-Ning Chou , Kamalika Chaudhuri

Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing…

Computation and Language · Computer Science 2022-09-14 Shihan Dou , Rui Zheng , Ting Wu , SongYang Gao , Junjie Shan , Qi Zhang , Yueming Wu , Xuanjing Huang

Predictive models -- learned from observational data not covering the complete data distribution -- can rely on spurious correlations in the data for making predictions. These correlations make the models brittle and hinder generalization.…

Machine Learning · Computer Science 2020-06-16 Khurram Javed , Martha White , Yoshua Bengio

Neural network classifiers can largely rely on simple spurious features, such as backgrounds, to make predictions. However, even in these cases, we show that they still often learn core features associated with the desired attributes of the…

Machine Learning · Computer Science 2023-07-04 Polina Kirichenko , Pavel Izmailov , Andrew Gordon Wilson

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 them for predictions,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Guangtao Zheng , Wenqian Ye , Aidong Zhang

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if…

Machine Learning · Computer Science 2023-08-09 Susu Sun , Lisa M. Koch , Christian F. Baumgartner

Generating calibrated and sharp neural network predictive distributions for regression problems is essential for optimal decision-making in many real-world applications. To address the miscalibration issue of neural networks, various…

Machine Learning · Computer Science 2024-03-19 Victor Dheur , Souhaib Ben Taieb

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Computation and Language · Computer Science 2021-10-08 Xiaochuang Han , Yulia Tsvetkov

Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approaches to suppress model reliance on harmful features have…

Machine Learning · Computer Science 2024-04-16 Dilyara Bareeva , Maximilian Dreyer , Frederik Pahde , Wojciech Samek , Sebastian Lapuschkin

Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a…

Machine Learning · Statistics 2025-05-29 Simone Bombari , Marco Mondelli

Some novel strategies have recently been proposed for single hidden layer neural network training that set randomly the weights from input to hidden layer, while weights from hidden to output layer are analytically determined by…

Machine Learning · Computer Science 2015-08-26 R. Cancelliere , R. Deluca , M. Gai , P. Gallinari , L. Rubini