English
Related papers

Related papers: Characterizing instance hardness in classification…

200 papers

Deep models trained with noisy labels are prone to over-fitting and struggle in generalization. Most existing solutions are based on an ideal assumption that the label noise is class-conditional, i.e., instances of the same class share the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Ganlong Zhao , Guanbin Li , Yipeng Qin , Feng Liu , Yizhou Yu

Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty…

Machine Learning · Computer Science 2022-05-30 Neeraj Varshney , Swaroop Mishra , Chitta Baral

We propose a new problem formulation which is similar to, but more informative than, the binary multiple-instance learning problem. In this setting, we are given groups of instances (described by feature vectors) along with estimates of the…

Machine Learning · Computer Science 2012-07-09 Hendrik Kuck , Nando de Freitas

Estimating the difficulty of a dataset typically involves comparing state-of-the-art models to humans; the bigger the performance gap, the harder the dataset is said to be. However, this comparison provides little understanding of how…

Computation and Language · Computer Science 2025-04-29 Kawin Ethayarajh , Yejin Choi , Swabha Swayamdipta

Characteristics extracted from the training datasets of classification problems have proven to be effective predictors in a number of meta-analyses. Among them, measures of classification complexity can be used to estimate the difficulty in…

Machine Learning · Computer Science 2021-01-01 Ana C. Lorena , Luís P. F. Garcia , Jens Lehmann , Marcilio C. P. Souto , Tin K. Ho

Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by…

Machine Learning · Computer Science 2020-12-04 Xiaobo Xia , Tongliang Liu , Bo Han , Nannan Wang , Mingming Gong , Haifeng Liu , Gang Niu , Dacheng Tao , Masashi Sugiyama

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Machine Learning · Computer Science 2022-02-09 Chidubem Arachie , Bert Huang

While generalization over tasks from easy to hard is crucial to profile language models (LLMs), the datasets with fine-grained difficulty annotations for each problem across a broad range of complexity are still blank. Aiming to address…

We investigate model based classification with partially labelled training data. In many biostatistical applications, labels are manually assigned by experts, who may leave some observations unlabelled due to class uncertainty. We analyse…

Methodology · Statistics 2019-04-08 Daniel Ahfock , Geoffrey J. McLachlan

A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard…

Machine Learning · Computer Science 2022-03-18 Xiao Zhang , David Evans

Model evaluation is a critical component in supervised machine learning classification analyses. Traditional metrics do not currently incorporate case difficulty. This renders the classification results unbenchmarked for generalization.…

Machine Learning · Computer Science 2023-02-10 Adrienne Kline , Joon Lee

Advances in dataset analysis techniques have enabled more sophisticated approaches to analyzing and characterizing training data instances, often categorizing data based on attributes such as ``difficulty''. In this work, we introduce…

Computation and Language · Computer Science 2024-10-15 Mohammad Reza Modarres , Sina Abbasi , Mohammad Taher Pilehvar

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Machine Learning · Computer Science 2021-03-31 Zhaowei Zhu , Tongliang Liu , Yang Liu

A supervised learning algorithm has access to a distribution of labeled examples, and needs to return a function (hypothesis) that correctly labels the examples. The hypothesis of the learner is taken from some fixed class of functions…

Machine Learning · Computer Science 2020-08-25 Eran Malach , Shai Shalev-Shwartz

In this paper, we investigate the effect of addressing difficult samples from a given text dataset on the downstream text classification task. We define difficult samples as being non-obvious cases for text classification by analysing them…

Computation and Language · Computer Science 2023-02-14 Shashank Mujumdar , Stuti Mehta , Hima Patel , Suman Mitra

In classifier (or regression) fusion the aim is to combine the outputs of several algorithms to boost overall performance. Standard supervised fusion algorithms often require accurate and precise training labels. However, accurate labels…

Computer Vision and Pattern Recognition · Computer Science 2019-02-19 Xiaoxiao Du , Alina Zare

In this paper, we tackle the problem of selecting the optimal model for a given structured pattern classification dataset. In this context, a model can be understood as a classifier and a hyperparameter configuration. The proposed…

Machine Learning · Computer Science 2022-10-27 Gonzalo Nápoles , Isel Grau , Çiçek Güven , Orçun Özdemir , Yamisleydi Salgueiro

Meta learning generalizes the empirical experience with different learning tasks and holds promise for providing important empirical insight into the behaviour of machine learning algorithms. In this paper, we present a comprehensive…

Machine Learning · Computer Science 2021-06-30 Jasmin Bogatinovski , Ljupčo Todorovski , Sašo Džeroski , Dragi Kocev

While research in robust optimization has attracted considerable interest over the last decades, its algorithmic development has been hindered by several factors. One of them is a missing set of benchmark instances that make algorithm…

Optimization and Control · Mathematics 2019-02-11 Marc Goerigk , Stephen J. Maher

ML models are typically trained using large datasets of high quality. However, training datasets often contain inconsistent or incomplete data. To tackle this issue, one solution is to develop algorithms that can check whether a prediction…

Machine Learning · Computer Science 2022-01-19 Austen Z. Fan , Paraschos Koutris