English
Related papers

Related papers: Avoiding Structural Failure Modes in Tabular Fair …

200 papers

In this paper, we focus on the out-of-distribution (OOD) generalization of self-supervised learning (SSL). By analyzing the mini-batch construction during the SSL training phase, we first give one plausible explanation for SSL having OOD…

Machine Learning · Computer Science 2025-05-23 Wenwen Qiang , Jingyao Wang , Zeen Song , Jiangmeng Li , Changwen Zheng

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Sebastian Scherer , Robin Schön , Rainer Lienhart

Algorithms designed for addressing typical supervised classification problems can only learn from a fixed set of samples and labels, making them unsuitable for the real world, where data arrives as a stream of samples often associated with…

Machine Learning · Computer Science 2024-02-08 Sourav Mishra , Shirin Dora , Suresh Sundaram

Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesome. Often, little is known about when and why an algorithm fails to outperform a supervised baseline. Using benchmark datasets, we craft five…

Unsupervised tabular anomaly detection methods typically learn feature patterns from normal samples during training and subsequently identify samples that deviate from these patterns as anomalies during testing. However, in practical…

Machine Learning · Computer Science 2026-05-12 Wei Huang , Hezhe Qiao , Kailai Zhang , Zaisheng Ye , Yu-Ming Shang , Xiangling Fu

Unsupervised Domain Adaptation (UDA) aims to align the labeled source distribution with the unlabeled target distribution to obtain domain invariant predictive models. However, the application of well-known UDA approaches does not…

Computer Vision and Pattern Recognition · Computer Science 2021-11-11 Ankit Singh

Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance, especially in 3D contexts. This study investigates class-level confidence as an indicator of learning…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Zhimin Chen , Bing Li

We study Stochastic Online Correlated Selection (SOCS), a family of online rounding algorithms for Non-IID Stochastic Online Submodular Welfare Maximization and special cases such as Online Stochastic Matching, Stochastic AdWords, and…

Data Structures and Algorithms · Computer Science 2024-08-23 Ziyun Chen , Zhiyi Huang , Enze Sun

Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as additional targets to train the model. We propose ProtoCon, a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Islam Nassar , Munawar Hayat , Ehsan Abbasnejad , Hamid Rezatofighi , Gholamreza Haffari

We derive an online learning algorithm with improved regret guarantees for `easy' loss sequences. We consider two types of `easiness': (a) stochastic loss sequences and (b) adversarial loss sequences with small effective range of the…

Machine Learning · Computer Science 2019-08-28 Tobias Sommer Thune , Yevgeny Seldin

Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these…

Machine Learning · Computer Science 2024-09-18 Zeju Li , Ying-Qiu Zheng , Chen Chen , Saad Jbabdi

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to…

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Mamshad Nayeem Rizve , Navid Kardan , Salman Khan , Fahad Shahbaz Khan , Mubarak Shah

Unsupervised domain adaptation (UDA) has achieved remarkable success in fault diagnosis, bringing significant benefits to diverse industrial applications. While most UDA methods focus on cross-working condition scenarios where the source…

Machine Learning · Computer Science 2024-05-29 Ziyan Wang , Mohamed Ragab , Wenmian Yang , Min Wu , Sinno Jialin Pan , Jie Zhang , Zhenghua Chen

Pseudo-labeling is a cornerstone of Unsupervised Domain Adaptation (UDA), yet the scarcity of High-Confidence Pseudo-Labeled Target Domain Samples (\textbf{hcpl-tds}) often leads to inaccurate cross-domain statistical alignment, causing DA…

Machine Learning · Computer Science 2025-05-13 Lingkun Luo , Shiqiang Hu , Liming Chen

We reinterpret some online greedy algorithms for a class of nonlinear "load-balancing" problems as solving a mathematical program online. For example, we consider the problem of assigning jobs to (unrelated) machines to minimize the sum of…

Data Structures and Algorithms · Computer Science 2011-09-28 Anupam Gupta , Ravishankar Krishnaswamy , Kirk Pruhs

Deep Neural Networks have significantly impacted many computer vision tasks. However, their effectiveness diminishes when test data distribution (target domain) deviates from the one of training data (source domain). In situations where…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Andrea Maracani , Lorenzo Rosasco , Lorenzo Natale

A major challenge that prevents the training of DL models is the limited availability of accurately labeled data. This shortcoming is highlighted in areas where data annotation becomes a time-consuming and error-prone task. In this regard,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 David Aparco-Cardenas , Jancarlo F. Gomes , Alexandre X. Falcão , Pedro J. de Rezende

Controlling false positives (Type I errors) through statistical hypothesis testing is a foundation of modern scientific data analysis. Existing causal structure discovery algorithms either do not provide Type I error control or cannot scale…

Methodology · Statistics 2025-12-29 James Leiner , Brian Manzo , Aaditya Ramdas , Wesley Tansey

Prediction-Powered Inference (PPI) is a recently proposed statistical inference technique for parameter estimation that leverages pseudo-labels on both labeled and unlabeled data to construct an unbiased, low-variance estimator. In this…

Machine Learning · Computer Science 2025-10-28 Noa Shoham , Ron Dorfman , Shalev Shaer , Kfir Y. Levy , Yaniv Romano
‹ Prev 1 3 4 5 6 7 10 Next ›