English
Related papers

Related papers: ShortcutProbe: Probing Prediction Shortcuts for Le…

200 papers

Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label…

Machine Learning · Computer Science 2025-05-28 Haosen Ge , Hamsa Bastani , Osbert Bastani

Deep Neural Networks (DNNs) are increasingly utilized in high-stakes domains like medical diagnostics and autonomous driving where model reliability is critical. However, the research landscape for ensuring this reliability is…

Machine Learning · Computer Science 2026-04-07 Ole Delzer , Sidney Bender

The expense of acquiring labels in large-scale statistical machine learning makes partially and weakly-labeled data attractive, though it is not always apparent how to leverage such data for model fitting or validation. We present a…

Machine Learning · Statistics 2022-02-10 Maxime Cauchois , Suyash Gupta , Alnur Ali , John Duchi

Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…

Machine Learning · Computer Science 2025-07-08 Jiashu Tao , Reza Shokri

Shortcut learning undermines model generalization to out-of-distribution data. While the literature attributes shortcuts to biases in superficial features, we show that imbalances in the semantic distribution of sample embeddings induce…

Machine Learning · Computer Science 2025-06-24 Shuo Yang , Bardh Prenkaj , Gjergji Kasneci

Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Aditya Parikh , Stella Frank , Sneha Das , Aasa Feragen

Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…

Machine Learning · Computer Science 2022-12-06 Deep Patel , P. S. Sastry

Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire. However, many existing methods are tailored to specific supervision…

Machine Learning · Computer Science 2025-12-01 Miao Zhang , Junpeng Li , Changchun Hua , Yana Yang

Few-shot node classification is tasked to provide accurate predictions for nodes from novel classes with only few representative labeled nodes. This problem has drawn tremendous attention for its projection to prevailing real-world…

Machine Learning · Computer Science 2022-12-13 Zhen Tan , Song Wang , Kaize Ding , Jundong Li , Huan Liu

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

Machine Learning · Computer Science 2020-06-15 Jun Shu , Qian Zhao , Zongben Xu , Deyu Meng

Recently, over-parameterized deep networks, with increasingly more network parameters than training samples, have dominated the performances of modern machine learning. However, when the training data is corrupted, it has been well-known…

Machine Learning · Computer Science 2022-08-04 Sheng Liu , Zhihui Zhu , Qing Qu , Chong You

Weakly-supervised learning is a paradigm for alleviating the scarcity of labeled data by leveraging lower-quality but larger-scale supervision signals. While existing work mainly focuses on utilizing a certain type of weak supervision, we…

Machine Learning · Statistics 2019-10-11 Yivan Zhang , Nontawat Charoenphakdee , Masashi Sugiyama

When a subgroup is identified from the data, it must be evaluated in a replicable way. The usual in-sample approach, which evaluates the post-hoc identified subgroup as predefined, might suffer from selection bias. This issue of in-sample…

Methodology · Statistics 2026-05-06 Shuoxun Xu , Xinzhou Guo

Many data mining and statistical machine learning algorithms have been developed to select a subset of covariates to associate with a response variable. Spurious discoveries can easily arise in high-dimensional data analysis due to enormous…

Statistics Theory · Mathematics 2016-10-25 Jianqing Fan , Wen-Xin Zhou

In learning with noisy labels, the sample selection approach is very popular, which regards small-loss data as correctly labeled during training. However, losses are generated on-the-fly based on the model being trained with noisy labels,…

Machine Learning · Computer Science 2021-06-02 Xiaobo Xia , Tongliang Liu , Bo Han , Mingming Gong , Jun Yu , Gang Niu , Masashi Sugiyama

Label noise poses an important challenge in machine learning, especially in deep learning, in which large models with high expressive power dominate the field. Models of that kind are prone to memorizing incorrect labels, thereby harming…

Machine Learning · Computer Science 2024-01-26 Julian Lienen , Eyke Hüllermeier

The ability to properly benchmark model performance in the face of spurious correlations is important to both build better predictors and increase confidence that models are operating as intended. We demonstrate that characterizing (as…

Machine Learning · Computer Science 2024-07-16 Isabela Albuquerque , Jessica Schrouff , David Warde-Farley , Taylan Cemgil , Sven Gowal , Olivia Wiles

Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to…

Machine Learning · Statistics 2018-11-16 Ian Osband , John Aslanides , Albin Cassirer

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…

Machine Learning · Computer Science 2024-09-25 Sjoerd de Vries , Dirk Thierens

Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Kilian Zepf , Eike Petersen , Jes Frellsen , Aasa Feragen