English
Related papers

Related papers: Selective Classification Under Distribution Shifts

200 papers

What sorts of structure might enable a learner to discover classes from unlabeled data? Traditional approaches rely on feature-space similarity and heroic assumptions on the data. In this paper, we introduce unsupervised learning under…

Machine Learning · Computer Science 2022-12-02 Manley Roberts , Pranav Mani , Saurabh Garg , Zachary C. Lipton

Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of…

Recent work on fractionally-supervised classification (FSC), an approach that allows classification to be carried out with a fractional amount of weight given to the unlabelled points, is further developed in two respects. The primary…

Methodology · Statistics 2017-09-26 Michael P. B. Gallaugher , Paul D. McNicholas

Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution, however in practice, this assumption is easily violated, as unlabeled data often includes unknown class data,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Heejo Kong , Sung-Jin Kim , Gunho Jung , Seong-Whan Lee

In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can…

Machine Learning · Computer Science 2017-12-21 Xiaowei Jia , Ankush Khandelwal , Anuj Karpatne , Vipin Kumar

Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image data sets, dataset explanation aims to automatically point…

Computation and Language · Computer Science 2022-07-01 Zhiying Zhu , Weixin Liang , James Zou

Semi-Supervised Learning (SSL) is a framework that utilizes both labeled and unlabeled data to enhance model performance. Conventional SSL methods operate under the assumption that labeled and unlabeled data share the same label space.…

Computer Vision and Pattern Recognition · Computer Science 2023-11-16 Noam Fluss , Guy Hacohen , Daphna Weinshall

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…

Machine Learning · Computer Science 2025-07-21 Mert Sehri , Zehui Hua , Francisco de Assis Boldt , Patrick Dumond

Large-scale datasets are increasingly being used to inform decision making. While this effort aims to ground policy in real-world evidence, challenges have arisen as selection bias and other forms of distribution shifts often plague…

Methodology · Statistics 2023-11-07 Santiago Cortes-Gomez , Mateo Dulce , Carlos Patino , Bryan Wilder

Recently there has been much work on selective sampling, an online active learning setting, in which algorithms work in rounds. On each round an algorithm receives an input and makes a prediction. Then, it can decide whether to query a…

Machine Learning · Computer Science 2014-02-18 Edward Moroshko , Koby Crammer

Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks. In this paper, we consider classification as a downstream task in phase 2 and develop rigorous theories to realize the factors…

Machine Learning · Computer Science 2023-05-18 Ngoc N. Tran , Son Duong , Hoang Phan , Tung Pham , Dinh Phung , Trung Le

In this paper, we present a deep extension of Sparse Subspace Clustering, termed Deep Sparse Subspace Clustering (DSSC). Regularized by the unit sphere distribution assumption for the learned deep features, DSSC can infer a new data…

Computer Vision and Pattern Recognition · Computer Science 2017-09-26 Xi Peng , Jiashi Feng , Shijie Xiao , Jiwen Lu , Zhang Yi , Shuicheng Yan

We introduce a novel end-to-end approach for learning to cluster in the absence of labeled examples. Our clustering objective is based on optimizing normalized cuts, a criterion which measures both intra-cluster similarity as well as…

Machine Learning · Computer Science 2019-10-18 Azade Nazi , Will Hang , Anna Goldie , Sujith Ravi , Azalia Mirhoseini

Due to the costliness of labelled data in real-world applications, semi-supervised learning, underpinned by pseudo labelling, is an appealing solution. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Changrui Chen , Jungong Han , Kurt Debattista

In many modern statistical problems, the limited available data must be used both to develop the hypotheses to test, and to test these hypotheses-that is, both for exploratory and confirmatory data analysis. Reusing the same dataset for…

Methodology · Statistics 2023-07-24 Youngjoo Yun , Rina Foygel Barber

The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully…

Artificial Intelligence · Computer Science 2026-01-09 Shogo Nakayama , Masahiro Okuda

Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data distribution shifts. We analyze the use of pseudo-calibration as a tool to…

Machine Learning · Computer Science 2026-02-17 Farbod Siahkali , Ashwin Verma , Vijay Gupta

Spectral clustering (SC) and graph-based semi-supervised learning (SSL) algorithms are sensitive to how graphs are constructed from data. In particular if the data has proximal and unbalanced clusters these algorithms can lead to poor…

Machine Learning · Statistics 2013-02-22 Jing Qian , Venkatesh Saligrama

A class of discrete probability distributions contains distributions with limited support, i.e. possible argument values are limited to a set of numbers (typically consecutive). Examples of such data are results from subjective experiments…

Methodology · Statistics 2019-09-11 Lucjan Janowski , Bogdan Ćmiel , Krzysztof Rusek , Jakub Nawała , Zhi Li

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment…

Machine Learning · Computer Science 2025-01-15 Yan Fan , Yu Wang , Pengfei Zhu , Qinghua Hu