Min-Ling Zhang

Partial Multi-Label Learning via Credible Label Elicitation

2020 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Partial multi-label learning (PML) deals with the problem where each training example is associated with an overcomplete set of candidate labels, among which only some candidate labels are valid. The task of PML naturally arises …

BiLabel-Specific Features for Multi-Label Classification

2021 · ACM Transactions on Knowledge Discovery from Data

In multi-label classification, the task is to induce predictive models which can assign a set of relevant labels for the unseen instance. The strategy of label-specific features has been widely employed in learning from multi-label …

Correlation-Guided Representation for Multi-Label Text Classification

2021

Multi-label text classification is an essential task in natural language processing. Existing multi-label classification models generally consider labels as categorical variables and ignore the exploitation of label semantics. In this paper, we view the task …

Partial-Label Regression

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Partial-label learning is a popular weakly supervised learning setting that allows each training example to be annotated with a set of candidate labels. Previous studies on partial-label learning only focused on the classification setting where …

Evolutionary Classifier Chain for Multi-Dimensional Classification

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

In multi-dimensional classification (MDC), the classifier chain approach is based on a chain structure to model dependencies between class spaces. However, current research on constructing a chain order is usually based on a greedy criterion …

Implicit Relative Labeling-Importance Aware Multi-Label Metric Learning

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Multi-label metric learning, as an extension of metric learning to multi-label scenarios, aims to learn better similarity metrics for objects with rich semantics. Existing multi-label metric learning approaches employ the common assumption of equal labeling-importance, …

LADA: Scalable Label-Specific CLIP Adapter for Continual Learning

2025 · arXiv (Cornell University)

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding multiple sets of learnable parameters, …