English
Related papers

Related papers: Causal Effect Regularization: Automated Detection …

200 papers

The predictions of text classifiers are often driven by spurious correlations -- e.g., the term `Spielberg' correlates with positively reviewed movies, even though the term itself does not semantically convey a positive sentiment. In this…

Machine Learning · Computer Science 2020-10-07 Zhao Wang , Aron Culotta

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

Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Yannic Neuhaus , Maximilian Augustin , Valentyn Boreiko , Matthias Hein

Learning representations unaffected by superficial characteristics is important to ensure that shifts in these characteristics at test time do not compromise downstream prediction performance. For instance, in healthcare applications, we…

Machine Learning · Computer Science 2025-07-28 Minghui Sun , Benjamin A. Goldstein , Matthew M. Engelhard

Unsupervised feature selection (UFS) has recently gained attention for its effectiveness in processing unlabeled high-dimensional data. However, existing methods overlook the intrinsic causal mechanisms within the data, resulting in the…

Machine Learning · Computer Science 2025-01-28 Zongxin Shen , Yanyong Huang , Dongjie Wang , Minbo Ma , Fengmao Lv , Tianrui Li

To capture the relationship between samples and labels, conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Junhyun Nam , Sangwoo Mo , Jaeho Lee , Jinwoo Shin

Shortcut learning, in which models make use of easy-to-represent but unstable associations, is a major failure mode for robust machine learning. We study a flexible, causally-motivated approach to training robust predictors by discouraging…

Machine Learning · Computer Science 2022-02-24 Maggie Makar , Ben Packer , Dan Moldovan , Davis Blalock , Yoni Halpern , Alexander D'Amour

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

Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. While most existing debiasing methods require full supervision on either spurious attributes or target labels, training a debiased…

Machine Learning · Computer Science 2023-10-10 Geon Yeong Park , Chanyong Jung , Sangmin Lee , Jong Chul Ye , Sang Wan Lee

Spurious correlations are a threat to the trustworthiness of natural language processing systems, motivating research into methods for identifying and eliminating them. However, addressing the problem of spurious correlations requires more…

Computation and Language · Computer Science 2022-05-05 Jacob Eisenstein

Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss. However, some of these features might be spuriously correlated with the target labels, leading to incorrect predictions by the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Shahin Hakemi , Naveed Akhtar , Ghulam Mubashar Hassan , Ajmal Mian

We study attribute control in language models through the method of Causal Average Treatment Effect (Causal ATE). Existing methods for the attribute control task in Language Models (LMs) check for the co-occurrence of words in a sentence…

Computation and Language · Computer Science 2024-02-19 Rahul Madhavan , Kahini Wadhawan

In unsupervised domain adaptation, existing theory focuses on situations where the source and target domains are close. In practice, conditional entropy minimization and pseudo-labeling work even when the domain shifts are much larger than…

Machine Learning · Computer Science 2020-12-09 Yining Chen , Colin Wei , Ananya Kumar , Tengyu Ma

Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character; e.g., changing the gender of a…

Machine Learning · Computer Science 2021-11-04 Victor Veitch , Alexander D'Amour , Steve Yadlowsky , Jacob Eisenstein

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP). Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and…

Computation and Language · Computer Science 2024-02-12 Lu Chen , Wei Huang , Ruqing Zhang , Wei Chen , Jiafeng Guo , Xueqi Cheng

Much recent work in NLP has documented dataset artifacts, bias, and spurious correlations between input features and output labels. However, how to tell which features have "spurious" instead of legitimate correlations is typically left…

Computation and Language · Computer Science 2021-12-30 Matt Gardner , William Merrill , Jesse Dodge , Matthew E. Peters , Alexis Ross , Sameer Singh , Noah A. Smith

A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output. However, if training data contains both causal and correlational relationships, a…

Machine Learning · Computer Science 2022-06-30 Sai Srinivas Kancheti , Abbavaram Gowtham Reddy , Vineeth N Balasubramanian , Amit Sharma

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

The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. To resolve this, recent works focus on developing weaker…

Machine Learning · Computer Science 2022-04-06 Junhyun Nam , Jaehyung Kim , Jaeho Lee , Jinwoo Shin

This paper frames causal structure estimation as a machine learning task. The idea is to treat indicators of causal relationships between variables as `labels' and to exploit available data on the variables of interest to provide features…

Machine Learning · Statistics 2019-10-17 Steven M. Hill , Chris. J. Oates , Duncan A. Blythe , Sach Mukherjee