Related papers: Provably Consistent Partial-Label Learning
Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue,…
In partial multi-label learning (PML), each instance is associated with a set of candidate labels containing both ground-truth and noisy labels. The presence of noisy labels disrupts the correspondence between features and labels, degrading…
A complementary label (CL) simply indicates an incorrect class of an example, but learning with CLs results in multi-class classifiers that can predict the correct class. Unfortunately, the problem setting only allows a single CL for each…
In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…
Obtaining high-quality labels for large datasets is expensive, requiring massive annotations from human experts. While AI models offer a cost-effective alternative by predicting labels, their label quality is compromised by the unavoidable…
Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class…
Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, given the fact that it could be expensive in practice to annotate all labels in every training…
Convolutional neural networks (CNNs) have gained increasing popularity and versatility in recent decades, finding applications in diverse domains. These remarkable achievements are greatly attributed to the support of extensive datasets…
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches…
Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances,…
In multi-task learning, labels are often missing irregularly across samples, which can be fully labeled, partially labeled or unlabeled. The irregular label presence often appears in scientific studies due to experimental limitations. It…
Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The straightforward combination of LT and PLL, i.e., LT-PLL,…
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a…
Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods…
Diminishing the impact of false-positive labels is critical for conducting disambiguation in partial label learning. However, the existing disambiguation strategies mainly focus on exploiting the characteristics of individual partial label…
Partial-Label Learning (PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error…
In reality, data often exhibit associations with multiple labels, making multi-label learning (MLL) become a prominent research topic. The last two decades have witnessed the success of MLL, which is indispensable from complete and accurate…
Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…
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…
Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric,…