English
Related papers

Related papers: Consistent Classification with Generalized Metrics

200 papers

To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models trained on the noisy…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Songzhu Zheng , Pengxiang Wu , Aman Goswami , Mayank Goswami , Dimitris Metaxas , Chao Chen

Machine learning-based classifiers are commonly evaluated by metrics like accuracy, but deeper analysis is required to understand their strengths and weaknesses. MLMC is a visual exploration tool that tackles the challenge of multi-label…

Machine Learning · Computer Science 2025-01-27 Aleksandar Doknic , Torsten Möller

For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essential aspects: training and validation, with which we address…

Machine Learning · Computer Science 2020-12-09 Pengfei Chen , Junjie Ye , Guangyong Chen , Jingwei Zhao , Pheng-Ann Heng

Meta learning uses information from base learners (e.g. classifiers or estimators) as well as information about the learning problem to improve upon the performance of a single base learner. For example, the Bayes error rate of a given…

Machine Learning · Computer Science 2016-03-11 Kevin R. Moon , Veronique Delouille , Alfred O. Hero

In this paper we study output coding for multi-label prediction. For a multi-label output coding to be discriminative, it is important that codewords for different label vectors are significantly different from each other. In the meantime,…

Machine Learning · Computer Science 2012-07-03 Yi Zhang , Jeff Schneider

This article explores the extension of well-known F1 score used for assessing the performance of binary classifiers. We propose the new metric using probabilistic interpretation of precision, recall, specificity, and negative predictive…

Machine Learning · Computer Science 2024-04-17 Mikolaj Sitarz

Given a learning problem with real-world tradeoffs, which cost function should the model be trained to optimize? This is the metric selection problem in machine learning. Despite its practical interest, there is limited formal guidance on…

Machine Learning · Statistics 2022-08-22 Gaurush Hiranandani

This paper discusses regularized estimators in the multivariate statistical model as tools naturally arising within a Bayesian framework. First, a link is established between Bayesian estimation and inference under parameter rounding…

Methodology · Statistics 2025-09-15 Jan Kalina

In this paper, a progressive learning algorithm for multi-label classification to learn new labels while retaining the knowledge of previous labels is designed. New output neurons corresponding to new labels are added and the neural network…

Machine Learning · Computer Science 2016-09-26 Mihika Dave , Sahil Tapiawala , Meng Joo Er , Rajasekar Venkatesan

We propose the family of generalized resubstitution classifier error estimators based on empirical measures. These error estimators are computationally efficient and do not require re-training of classifiers. The plain resubstitution error…

Machine Learning · Statistics 2021-10-26 Parisa Ghane , Ulisses Braga-Neto

We present a conceptual framework that unifies a variety of evaluation metrics for different structured prediction tasks (e.g. event and relation extraction, syntactic and semantic parsing). Our framework requires representing the outputs…

Computation and Language · Computer Science 2023-10-24 Yunmo Chen , William Gantt , Tongfei Chen , Aaron Steven White , Benjamin Van Durme

In most classification tasks there are observations that are ambiguous and therefore difficult to correctly label. Set-valued classifiers output sets of plausible labels rather than a single label, thereby giving a more appropriate and…

Methodology · Statistics 2018-12-27 Mauricio Sadinle , Jing Lei , Larry Wasserman

We provide a unifying view of statistical information measures, multi-way Bayesian hypothesis testing, loss functions for multi-class classification problems, and multi-distribution $f$-divergences, elaborating equivalence results between…

Statistics Theory · Mathematics 2017-09-12 John C. Duchi , Khashayar Khosravi , Feng Ruan

A large number and diversity of techniques have been offered in the literature in recent years for solving multi-label classification tasks, including classifier chains where predictions are cascaded to other models as additional features.…

Machine Learning · Computer Science 2019-07-19 Jesse Read , Luca Martino

New proposed models are often compared to state-of-the-art using statistical significance testing. Literature is scarce for classifier comparison using metrics other than accuracy. We present a survey of statistical methods that can be used…

Machine Learning · Computer Science 2016-11-17 Lovedeep Gondara

Multi-class classification methods that produce sets of probabilistic classifiers, such as ensemble learning methods, are able to model aleatoric and epistemic uncertainty. Aleatoric uncertainty is then typically quantified via the Bayes…

Machine Learning · Statistics 2023-04-20 Thomas Mortier , Viktor Bengs , Eyke Hüllermeier , Stijn Luca , Willem Waegeman

Understanding how different classes are distributed in an unlabeled data set is an important challenge for the calibration of probabilistic classifiers and uncertainty quantification. Approaches like adjusted classify and count, black-box…

Machine Learning · Statistics 2024-06-19 Albert Ziegler , Paweł Czyż

Multi-dimensional classification (MDC) can be employed in a range of applications where one needs to predict multiple class variables for each given instance. Many existing MDC methods suffer from at least one of inaccuracy, scalability,…

Machine Learning · Computer Science 2023-11-28 Vu-Linh Nguyen , Yang Yang , Cassio de Campos

The question of whether to use one classifier or a combination of classifiers is a central topic in Machine Learning. We propose here a method for finding an optimal linear combination of classifiers derived from a bias-variance framework…

Machine Learning · Computer Science 2021-03-02 Georgi Nalbantov , Svetoslav Ivanov

Unlike the typical classification setting where each instance is associated with a single class, in multi-label learning each instance is associated with multiple classes simultaneously. Therefore the learning task in this setting is to…

Machine Learning · Computer Science 2022-11-30 Harris Papadopoulos