English
Related papers

Related papers: The Oracle of DLphi

200 papers

State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making…

Machine Learning · Computer Science 2022-06-20 Michael Hedderich , Jonas Fischer , Dietrich Klakow , Jilles Vreeken

In semi-supervised representation learning frameworks, when the number of labelled data is very scarce, the quality and representativeness of these samples become increasingly important. Existing literature on semi-supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Shuvendu Roy , Ali Etemad

Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the label delay, where new data may not be labeled due to slow and…

Machine Learning · Computer Science 2024-04-29 Botos Csaba , Wenxuan Zhang , Matthias Müller , Ser-Nam Lim , Mohamed Elhoseiny , Philip Torr , Adel Bibi

Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However,…

Machine Learning · Computer Science 2019-09-10 Che-Ping Tsai , Hung-Yi Lee

AI systems often struggle to provide reliable predictions across all inputs, motivating hybrid human-AI decision-making. Existing Learning to Defer (L2D) approaches address this by training models to selectively defer to human experts.…

Machine Learning · Computer Science 2026-03-31 Tim Bary , Benoît Macq , Louis Petit

Recent deep learning models for tabular data currently compete with the traditional ML models based on decision trees (GBDT). Unlike GBDT, deep models can additionally benefit from pretraining, which is a workhorse of DL for vision and NLP.…

Machine Learning · Computer Science 2022-07-13 Ivan Rubachev , Artem Alekberov , Yury Gorishniy , Artem Babenko

Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually…

Machine Learning · Computer Science 2022-01-06 Ruihan Wu , Chuan Guo , Yi Su , Kilian Q. Weinberger

Decision-Focused Learning (DFL) is an emerging learning paradigm that tackles the task of training a machine learning (ML) model to predict missing parameters of an incomplete optimization problem, where the missing parameters are…

Machine Learning · Computer Science 2025-06-23 Yehya Farhat

Machine learning may enable the automated generation of test oracles. We have characterized emerging research in this area through a systematic literature review examining oracle types, researcher goals, the ML techniques applied, how the…

Software Engineering · Computer Science 2021-08-10 Afonso Fontes , Gregory Gay

Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance…

Machine Learning · Computer Science 2024-12-13 Jian Liang , Ran He , Tieniu Tan

Real-world datasets are dirty and contain many errors. Examples of these issues are violations of integrity constraints, duplicates, and inconsistencies in representing data values and entities. Learning over dirty databases may result in…

Databases · Computer Science 2020-04-07 Jose Picado , John Davis , Arash Termehchy , Ga Young Lee

The success stories from deep learning models increase every day spanning different tasks from image classification to natural language understanding. With the increasing popularity of these models, scientists spend more and more time…

Computer Vision and Pattern Recognition · Computer Science 2020-09-29 Ethem F. Can , Aysu Ezen-Can

In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets…

Machine Learning · Computer Science 2018-11-16 Matthew Klawonn , Eric Heim , James Hendler

Lifelong Learning (LL) refers to the ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Much attention has been given lately to Supervised Lifelong…

Machine Learning · Computer Science 2021-06-17 Tingting Zhao , Zifeng Wang , Aria Masoomi , Jennifer Dy

Deep learning (DL) is gaining popularity as a parameter estimation method for quantitative MRI. A range of competing implementations have been proposed, relying on either supervised or self-supervised learning. Self-supervised approaches,…

Medical Physics · Physics 2024-01-24 Sean C. Epstein , Timothy J. P. Bray , Margaret Hall-Craggs , Hui Zhang

Self-training algorithms, which train a model to fit pseudolabels predicted by another previously-learned model, have been very successful for learning with unlabeled data using neural networks. However, the current theoretical…

Machine Learning · Computer Science 2022-04-22 Colin Wei , Kendrick Shen , Yining Chen , Tengyu Ma

Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in…

Machine Learning · Computer Science 2015-02-19 Fangfang Li , Guandong Xu , Longbing Cao

Motivated by problems in online advertising, we address the task of Learning from Label Proportions (LLP). We introduce a novel and versatile low-variance debiasing methodology to learn from aggregate label information, significantly…

Machine Learning · Computer Science 2026-02-02 Lorne Applebaum , Travis Dick , Claudio Gentile , Haim Kaplan , Tomer Koren

We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these techniques for supervised learning, we establish a connection between…

Machine Learning · Computer Science 2016-11-28 Maria Florina Balcan , Travis Dick , Yishay Mansour

Most classifiers operate by selecting the maximum of an estimate of the conditional distribution $p(y|x)$ where $x$ stands for the features of the instance to be classified and $y$ denotes its label. This often results in a {\em hubristic…

Machine Learning · Statistics 2019-03-01 Yotam Hechtlinger , Barnabás Póczos , Larry Wasserman