Related papers: Optimizing Classification of Infrequent Labels by …
Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected…
We introduce a new framework for analyzing classification datasets based on the ratios of reconstruction errors between autoencoders trained on individual classes. This analysis framework enables efficient characterization of datasets on…
There is often a mixture of very frequent labels and very infrequent labels in multi-label datatsets. This variation in label frequency, a type class imbalance, creates a significant challenge for building efficient multi-label…
In multi-label classification, an instance may be associated with a set of labels simultaneously. Recently, the research on multi-label classification has largely shifted its focus to the other end of the spectrum where the number of labels…
This paper focuses on the task of Extreme Multi-Label Classification (XMC) whose goal is to predict multiple labels for each instance from an extremely large label space. While existing research has primarily focused on fully supervised…
Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…
Compared with multi-class classification, multi-label classification that contains more than one class is more suitable in real life scenarios. Obtaining fully labeled high-quality datasets for multi-label classification problems, however,…
Extreme multi-label classification (XMC) aims to identify relevant subsets from numerous labels. Among the various approaches for XMC, tree-based linear models are effective due to their superior efficiency and simplicity. However, the…
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…
Label distribution learning (LDL) differs from multi-label learning which aims at representing the polysemy of instances by transforming single-label values into descriptive degrees. Unfortunately, the feature space of the label…
Although \textbf{L}abel \textbf{D}istribution \textbf{L}earning (LDL) has promising representation capabilities for characterizing the polysemy of an instance, the complexity and high cost of the label distribution annotation lead to…
Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire…
Deep imbalanced regression (DIR), where the target values have a highly skewed distribution and are also continuous, is an intriguing yet under-explored problem in machine learning. While recent works have already shown that incorporating…
We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into "bags", and only the frequency of class labels at each bag is available. Albeit, the objective of…
Transductive graph-based semi-supervised learning methods usually build an undirected graph utilizing both labeled and unlabeled samples as vertices. Those methods propagate label information of labeled samples to neighbors through their…
High-quality data is crucial for the success of machine learning, but labeling large datasets is often a time-consuming and costly process. While semi-supervised learning can help mitigate the need for labeled data, label quality remains an…
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…
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…
We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification that are formulated from distributionally robust optimization (DRO) perspective, where the uncertainty in the given label…
Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…