English
Related papers

Related papers: Severing Spurious Correlations with Data Pruning

200 papers

The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data. For example, a classifier may misclassify dog breeds based on the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Aengus Lynch , Gbètondji J-S Dovonon , Jean Kaddour , Ricardo Silva

Due to their high degree of expressiveness, neural networks have recently been used as surrogate models for mapping inputs of an engineering system to outputs of interest. Once trained, neural networks are computationally inexpensive to…

Machine Learning · Statistics 2020-02-12 Subhayan De , Jolene Britton , Matthew Reynolds , Ryan Skinner , Kenneth Jansen , Alireza Doostan

Recent work has shown that deep learning models in NLP are highly sensitive to low-level correlations between simple features and specific output labels, leading to overfitting and lack of generalization. To mitigate this problem, a common…

Computation and Language · Computer Science 2022-04-28 Roy Schwartz , Gabriel Stanovsky

The existing algorithms for identification of neurons responsible for undesired and harmful behaviors do not consider the effects of confounders such as topic of the conversation. In this work, we show that confounders can create spurious…

Computation and Language · Computer Science 2024-12-05 Milad Fotouhi , Mohammad Taha Bahadori , Oluwaseyi Feyisetan , Payman Arabshahi , David Heckerman

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

In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective. When focussing on the way in which the training data are…

Machine Learning · Computer Science 2021-06-22 Simone Marullo , Matteo Tiezzi , Marco Gori , Stefano Melacci

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks…

Machine Learning · Statistics 2017-11-15 Michael Zhu , Suyog Gupta

While data are the primary fuel for machine learning models, they often suffer from missing values, especially when collected in real-world scenarios. However, many off-the-shelf machine learning models, including artificial neural network…

Practitioners prune neural networks for efficiency gains and generalization improvements, but few scrutinize the factors determining the prunability of a neural network the maximum fraction of weights that pruning can remove without…

Machine Learning · Computer Science 2022-12-02 Zachary Ankner , Alex Renda , Gintare Karolina Dziugaite , Jonathan Frankle , Tian Jin

The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spurious features from the model. However, in this work we show…

Machine Learning · Computer Science 2020-12-09 Fereshte Khani , Percy Liang

Neural networks can fail when the data contains spurious correlations. To understand this phenomenon, researchers have proposed numerous spurious correlations benchmarks upon which to evaluate mitigation methods. However, we observe that…

Machine Learning · Computer Science 2024-09-09 Samuel J. Bell , Diane Bouchacourt , Levent Sagun

Spurious correlations allow flexible models to predict well during training but poorly on related test distributions. Recent work has shown that models that satisfy particular independencies involving correlation-inducing \textit{nuisance}…

Machine Learning · Computer Science 2022-06-10 Mark Goldstein , Jörn-Henrik Jacobsen , Olina Chau , Adriel Saporta , Aahlad Puli , Rajesh Ranganath , Andrew C. Miller

Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural…

Signal Processing · Electrical Eng. & Systems 2023-11-15 Weidong Wang , Hongshu Liao , Lu Gan

Model substructure learning aims to find an invariant network substructure that can have better out-of-distribution (OOD) generalization than the original full structure. Existing works usually search the invariant substructure using…

Machine Learning · Computer Science 2023-06-05 Yingchun Wang , Jingcai Guo , Yi Liu , Song Guo , Weizhan Zhang , Xiangyong Cao , Qinghua Zheng

The robustness and anomaly detection capability of neural networks are crucial topics for their safe adoption in the real-world. Moreover, the over-parameterization of recent networks comes with high computational costs and raises questions…

Machine Learning · Computer Science 2022-07-12 Morgane Ayle , Bertrand Charpentier , John Rachwan , Daniel Zügner , Simon Geisler , Stephan Günnemann

Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. In this work, we…

Machine Learning · Computer Science 2024-07-18 Jing Wu , Mehrtash Harandi

Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the…

Machine Learning · Computer Science 2018-07-17 Amirsina Torfi , Rouzbeh A. Shirvani , Sobhan Soleymani , Nasser M. Nasrabadi

Neural networks are prone to be biased towards spurious correlations between classes and latent attributes exhibited in a major portion of training data, which ruins their generalization capability. We propose a new method for training…

Machine Learning · Computer Science 2023-05-02 Nayeong Kim , Sehyun Hwang , Sungsoo Ahn , Jaesik Park , Suha Kwak

To address the problem of NLP classifiers learning spurious correlations between training features and target labels, a common approach is to make the model's predictions invariant to these features. However, this can be counter-productive…

Machine Learning · Computer Science 2023-06-22 Parikshit Bansal , Amit Sharma

Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others. This shortcut learning behaviour is detrimental to a network's ability to generalize to…

Machine Learning · Computer Science 2023-01-11 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen