Related papers: Concentration Distribution Learning from Label Dis…

Curriculum learning can improve neural network training by guiding the optimization to desirable optima. We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label…

Complementary-label Learning (CLL) is a form of weakly supervised learning that trains an ordinary classifier using only complementary labels, which are the classes that certain instances do not belong to. While existing CLL studies…

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…

Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags, and the label proportions within each bag are observed instead of the instance-level labels. The task is to learn a…

Learning from Label Proportions (LLP) is a weakly supervised problem in which the training data comprise bags, that is, groups of instances, each annotated only with bag-level class label proportions, and the objective is to learn a…

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…

Time series forecasting in real-world applications requires both high predictive accuracy and interpretable uncertainty quantification. Traditional point prediction methods often fail to capture the inherent uncertainty in time series data,…

As a prominent challenge in addressing real-world issues within a dynamic environment, label shift, which refers to the learning setting where the source (training) and target (testing) label distributions do not match, has recently…

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…

Label distribution (LD) uses the description degree to describe instances, which provides more fine-grained supervision information when learning with label ambiguity. Nevertheless, LD is unavailable in many real-world applications. To…

As data volumes continue to grow, the labelling process increasingly becomes a bottleneck, creating demand for methods that leverage information from unlabelled data. Impressive results have been achieved in semi-supervised learning (SSL)…

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently…

Learning with label proportions (LLP), which is a learning task that only provides unlabeled data in bags and each bag's label proportion, has widespread successful applications in practice. However, most of the existing LLP methods don't…

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…

Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain invariant optimal…

Causal deep learning (CDL) is a new and important research area in the larger field of machine learning. With CDL, researchers aim to structure and encode causal knowledge in the extremely flexible representation space of deep learning…

Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail…

Real-world training data is often noisy; for example, human annotators assign conflicting class labels to the same instances. Partial-label learning (PLL) is a weakly supervised learning paradigm that allows training classifiers in this…

Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user…

Conventional multi-label classification (MLC) methods assume that all samples are fully labeled and identically distributed. Unfortunately, this assumption is unrealistic in large-scale MLC data that has long-tailed (LT) distribution and…