Label Distribution Imputation and Bias-Corrective Representation Learning for Incomplete and Imbalanced Label Distribution

ComRank: Ranking Loss for Multi-Label Complementary Label Learning

Multi-label complementary label learning (MLCLL) is a weakly supervised paradigm that addresses multi-label learning (MLL) tasks using complementary labels (i.e., irrelevant labels) instead of relevant labels. Existing methods typically adopt an unbiased risk estimator (URE) under the assumption that complementary labels follow a uniform distribution. However, this assumption fails in real-world scenarios due to instance-specific annotation biases, making URE-based methods ineffective under such conditions. Furthermore, existing methods un-derutilize label correlations inherent in MLL. To address these limitations, we propose ComRank , a ranking loss framework for MLCLL, which encourages complementary labels to be ranked lower than non-complementary ones, thereby modeling pairwise label relationships. Theoretically, our surrogate loss ensures Bayes consistency under both uniform and biased cases. Experiments demonstrate the effectiveness of our method in MLCLL tasks. The code is available at https://github.com/JellyJamZhu/ComRank.

Debiased label enhancement for class-imbalanced semi-supervised learning

Distribution-aware probability contrastive learning for class-imbalanced semi-supervised learning

Semi-Supervised Learning (SSL) has shown significant advantages by leveraging abundant unlabeled data to enhance model performance with successful applications in computer vision. However, existing SSL methods might exhibit significant performance degradation in real applications, primarily due to the learning bias stemming from the following two challenges: (1) the occurrence of class imbalance in real-world datasets, and (2) the misalignment between class distributions of labeled and unlabeled data. To deal with the above challenges, current Class-Imbalanced SSL (CISSL) methods mainly resorted to data rebalancing strategies (e.g., resampling) and failed to fully exploit the high-level distributional characteristics. To address this problem, a novel solution termed Distribution-Aware Probability Contrastive Learning (DPCL) is proposed in this work. In DPCL, contrastive learning was leveraged to learn better representation distributions by uniformly projecting data on a hypersphere, and by which more accurate pseudo labels could be generated. To evaluate the classification performance of DPCL, we conduct extensive experiments on benchmark class-imbalanced SSL datasets. The results demonstrate that DPCL achieves consistent improvements over existing state-of-the-art methods across multiple benchmarks.

DAPR: Dynamic Distribution-Aware and Adaptive Pseudo-Label Refinement for Long-Tailed Semi-Supervised Oral Disease Classification

Oral disease image classification can support computer-assisted assessment of intraoral images. However, obtaining large-scale annotated medical data is expensive, while real-world oral disease datasets often exhibit severe long-tailed distributions, where minority disease categories contain only limited samples. Existing semi-supervised learning methods commonly rely on fixed-threshold pseudo labels and may produce prediction distributions dominated by majority classes, resulting in class bias and pseudo-label noise accumulation under long-tailed settings. To address these issues, we propose DAPR, a Distribution-Aware and Adaptive Pseudo-Label Refinement framework for long-tailed semi-supervised oral disease classification. DAPR employs Dynamic Category Distribution Modeling (DCDM) to track the evolving prediction distribution of unlabeled samples and generate distribution-aware soft pseudo labels. A class-adaptive dynamic thresholding (CADT) mechanism was further introduced to improve minority-class sample utilization. In addition, Relation-aware Representation Learning (RRL) aligns semantic and feature relationships to enhance feature discrimination. Experiments using stratified five-fold cross-validation on a long-tailed oral disease dataset show that DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods under the evaluated setting. DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers. These results indicate that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.

Learning from Uncertainty-dependent Missing Labels for Semi-supervised Classification

Missing labels are usually regarded as a source of information loss in classification. We study a semi-supervised setting in which the probability of label missingness depends on the observed features through posterior classification uncertainty. In this setting, the missingness indicator is not only a record of an unobserved label, but also an observable signal generated by a mechanism linked to the classifier. We develop a likelihood-based information theory for such uncertainty-dependent missing labels. Under correct specification, we derive a Fisher-information decomposition that separates a partial-labeling component from a nonnegative mechanism-curvature term. Under joint misspecification of the label model and the missingness mechanism, we obtain the corresponding Godambe--Eicker--Huber--White sensitivity and sandwich-covariance partitions. We also clarify the relevant complete-data benchmark: favorable missingness can increase information relative to ordinary fully labeled or budget-matched non-informative labeling baselines, but cannot exceed the information in the augmented experiment in which labels and mechanism indicators are both observed. For plug-in classifiers, we connect the information decomposition to margin-based excess-risk bounds. In regular two-component mixture settings this yields the parametric \(n^{-1}\) excess-risk rate, with constants determined by the nuisance-adjusted information in discriminant directions. Gaussian-mixture calculations and a medical diagnosis example illustrate how uncertainty-dependent labeling mechanisms can improve estimation and classification under a fixed labeling budget.

Conformal prediction for multi-label learning: a review of methods and guarantees.

Multi-label learning (MLL) is a machine learning paradigm that aims to predict a set of labels for each instance, rather than a single class. Such tasks arise in a wide range of real-world applications and pose significant challenges, including an exponentially large output space, dependence among labels and often severe label imbalance. These challenges amplify predictive uncertainty, making reliable uncertainty quantification essential. Conformal prediction (CP) is an attractive answer: it converts model outputs into prediction regions with distribution-free, finite-sample guarantees under the sole assumption of data exchangeability. Several adaptations of CP to the multi-label setting have been proposed. Yet these vary widely in scoring constructions, output types and targeted guarantees. This review consolidates the landscape of CP adaptations for MLL. It places existing approaches under a unified framework, examining the types of outputs and guarantees they provide, where label dependencies are incorporated, and how inference cost scales with the number of labels. It provides an in-depth analysis of all approaches using common notation, identifying their key characteristics along with their practical implications and assessing their strengths and limitations. Finally, it compares approaches side-by-side, highlighting trade-offs among guarantee types, precision of regions, compactness of outputs and scalability. This article is part of the theme issue 'Advancing uncertainty quantification in AI systems'.