English
Related papers

Related papers: Towards Debiasing NLU Models from Unknown Biases

200 papers

Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Eungyeup Kim , Jihyeon Lee , Jaegul Choo

Despite numerous efforts to mitigate their biases, ML systems continue to harm already-marginalized people. While predominant ML approaches assume bias can be removed and fair models can be created, we show that these are not always…

Computation and Language · Computer Science 2025-04-02 Lucy Havens , Benjamin Bach , Melissa Terras , Beatrice Alex

Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…

Human-Computer Interaction · Computer Science 2022-03-02 Wencan Zhang , Mariella Dimiccoli , Brian Y. Lim

Calibration of neural networks is a topical problem that is becoming more and more important as neural networks increasingly underpin real-world applications. The problem is especially noticeable when using modern neural networks, for which…

Machine Learning · Computer Science 2023-08-29 Ondrej Bohdal , Yongxin Yang , Timothy Hospedales

As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor…

Computer Vision and Pattern Recognition · Computer Science 2021-11-10 Jiazhi Li , Wael Abd-Almageed

This paper provides an introduction to Double/Debiased Machine Learning (DML). DML is a general approach to performing inference about a target parameter in the presence of nuisance functions: objects that are needed to identify the target…

Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks, however they sometimes fail to maintain crucial invariances for specific tasks. One example is permutation sensitivity, where…

Computation and Language · Computer Science 2024-03-21 Adian Liusie , Yassir Fathullah , Mark J. F. Gales

Neural networks often learn spurious correlations when exposed to biased training data, leading to poor performance on out-of-distribution data. A biased dataset can be divided, according to biased features, into bias-aligned samples (i.e.,…

Machine Learning · Computer Science 2023-08-17 Rui Hu , Yahan Tu , Jitao Sang

While automated driving technology has achieved a tremendous progress, the scalable and rigorous testing and verification of safe automated and autonomous driving vehicles remain challenging. This paper proposes a learning-based…

Robotics · Computer Science 2021-01-27 Andrea Favrin , Vladislav Nenchev , Angelo Cenedese

Existing techniques for mitigating dataset bias often leverage a biased model to identify biased instances. The role of these biased instances is then reduced during the training of the main model to enhance its robustness to…

Machine Learning · Computer Science 2021-09-03 Hossein Amirkhani , Mohammad Taher Pilehvar

In image classification, "debiasing" aims to train a classifier to be less susceptible to dataset bias, the strong correlation between peripheral attributes of data samples and a target class. For example, even if the frog class in the…

Computer Vision and Pattern Recognition · Computer Science 2022-12-08 Jungsoo Lee , Jeonghoon Park , Daeyoung Kim , Juyoung Lee , Edward Choi , Jaegul Choo

Debiased inference for high-dimensional regression models has received substantial recent attention to ensure regularized estimators have valid inference. All existing methods focus on achieving Neyman orthogonality through explicitly…

Methodology · Statistics 2025-12-16 Yi Wang , Yuhao Deng , Yu Gu , Yuanjia Wang , Donglin Zeng

We study methods for simultaneous analysis of many noisy and biased estimates, each paired with an even noisier estimate of its own bias. The analyst's goal is to construct short calibrated intervals for each parameter. The standard…

Methodology · Statistics 2026-05-11 Wanyi Ling , Sida Li , Junming Guan , Nikolaos Ignatiadis

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

Machine Learning · Computer Science 2022-10-18 Xudong Han , Aili Shen , Trevor Cohn , Timothy Baldwin , Lea Frermann

Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations…

Machine Learning · Computer Science 2024-11-04 Yeonsung Jung , Jaeyun Song , June Yong Yang , Jin-Hwa Kim , Sung-Yub Kim , Eunho Yang

Learning to rank with biased click data is a well-known challenge. A variety of methods has been explored to debias click data for learning to rank such as click models, result interleaving and, more recently, the unbiased learning-to-rank…

Information Retrieval · Computer Science 2018-04-25 Qingyao Ai , Keping Bi , Cheng Luo , Jiafeng Guo , W. Bruce Croft

Advances in machine learning and the increasing availability of high-dimensional data have led to the proliferation of social science research that uses the predictions of machine learning models as proxies for measures of human activity or…

Machine Learning · Computer Science 2025-02-19 Luke C Sanford , Megan Ayers , Matthew Gordon , Eliana Stone

Removing bias while keeping all task-relevant information is challenging for fair representation learning methods since they would yield random or degenerate representations w.r.t. labels when the sensitive attributes correlate with labels.…

Machine Learning · Computer Science 2022-08-02 Yixuan Zhang , Feng Zhou , Zhidong Li , Yang Wang , Fang Chen

Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainties by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have…

Machine Learning · Statistics 2021-12-17 Sujay Thakur , Cooper Lorsung , Yaniv Yacoby , Finale Doshi-Velez , Weiwei Pan

Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for…

Computation and Language · Computer Science 2023-07-25 Somayeh Ghanbarzadeh , Yan Huang , Hamid Palangi , Radames Cruz Moreno , Hamed Khanpour
‹ Prev 1 8 9 10 Next ›