Chong Liu, Peng Zhao, Sheng-Jun Huang, Yuan Jiang, Zhi-Hua Zhou 1 National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China 2 Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210023, China 3 College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China {liuc,...

Multi-label classification deals with problems in which each instance can be associated with a set of labels. An effective multi-label method, named RAkEL, randomly breaks the initial set of labels into smaller sets and trains a single-label classifier in each of this subset. To classify an unseen instance, the predictions of all classifiers are combined using a voting process. In this paper, w...

Most classification problems associate a single class to each example or instance. However, there are many classification tasks where each instance can be associated with one or more classes. This group of problems represents an area known as multi-label classification. One typical example of multi-label classification problems is the classification of documents, where each document can be assi...

Multi-label text classification (MLTC) involves tagging a document with its most relevant subset of labels from label set. In real applications, usually follow long-tailed distribution, where (called as tail-label) only contain small number documents and limit the performance MLTC. To facilitate this low-resource problem, researchers introduced simple but effective strategy, data augmentation (...

Multi-label text classification (MLTC) aims to annotate documents with the most relevant labels from a number of candidate labels. In real applications, distribution label frequency often exhibits long tail, i.e., few are associated large (a.k.a. head labels), while fraction small tail labels). To address challenge insufficient training data on classification, we propose Head-to-Tail Network (H...

Data representation is of significant importance in minimizing multi-label ambiguity. While most researchers intensively investigate label correlation, the research on enhancing model robustness preliminary. Low-quality data one main reasons that degrades. Aiming at cases with noisy features and missing labels, we develop a novel method called robust global local correlation (RGLC). In this mod...

Most of the text classification problems are associated with multiple class labels and hence automatic text classification is one of the most challenging and prominent research area. Text classification is the problem of categorizing text documents into different classes. In the multi-label classification scenario, each document is associated may have more than one label. The real challenge in ...

Real-world recognition system often encounters the challenge of unseen labels. To identify such labels, multi-label zero-shot learning (ML-ZSL) focuses on transferring knowledge by a pre-trained textual label embedding (e.g., GloVe). However, methods only exploit single-modal from language model, while ignoring rich semantic information inherent in image-text pairs. Instead, recently developed ...