Multi-Label Learning
81 papers with code • 1 benchmarks • 8 datasets
Multi-label learning (MLL) is a generalization of the binary and multi-category classification problems and deals with tagging a data instance with several possible class labels simultaneously [1]. Each of the assigned labels conveys a specific semantic relationship with the multi-label data instance [2, 3]. Multi-label learning has continued to receive a lot of research interest due to its practical application in many real-world problems such as recommender systems [4], image annotation [5], and text classification [6].
References:
-
Kumar, S., Rastogi, R., Low rank label subspace transformation for multi-label learning with missing labels. Information Sciences 596, 53–72 (2022)
-
Zhang M-L, Zhou Z-H (2013) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837
-
Gibaja E, Ventura S (2015) A tutorial on multilabel learning. ACM Comput Surveys (CSUR) 47(3):1–38
-
Bogaert M, Lootens J, Van den Poel D, Ballings M (2019) Evaluating multi-label classifiers and recommender systems in the financial service sector. Eur J Oper Res 279(2):620– 634
-
Jing L, Shen C, Yang L, Yu J, Ng MK (2017) Multi-label classification by semi-supervised singular value decomposition. IEEE Trans Image Process 26(10):4612–4625
-
Chen Z, Ren J (2021) Multi-label text classification with latent word-wise label information. Appl Intell 51(2):966–979
Datasets
MS COCO
ExpW
BirdSong
Animal Kingdom
MIMIC Meme Dataset
Corn Seeds Dataset
Latest papers
Towards Understanding Generalization of Macro-AUC in Multi-label Learning
We theoretically identify a critical factor of the dataset affecting the generalization bounds: \emph{the label-wise class imbalance}.
Auxiliary Label Embedding for Multi-label Learning with Missing Labels
Label correlation has been exploited for multi-label learning in different ways.
Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning
Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data.
Light-weight Deep Extreme Multilabel Classification
Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels.
MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning
zeroqiaoba/mer2023-baseline
•
•
The first Multimodal Emotion Recognition Challenge (MER 2023) was successfully held at ACM Multimedia.
Deep Double Incomplete Multi-view Multi-label Learning with Incomplete Labels and Missing Views
justsmart/DIMC-mindspore
•
•
IEEE Transactions on Neural Networks and Learning Systems 2023
View missing and label missing are two challenging problems in the applications of multi-view multi-label classification scenery.
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification
justsmart/DICNet
•
•
To deal with the double incomplete multi-view multi-label classification problem, we propose a deep instance-level contrastive network, namely DICNet.
Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers
justsmart/LMVCAT
•
•
The former aggregates information from different views in the process of extracting view-specific features, and the latter learns subcategory embedding to improve classification performance.
Multi-label learning with missing labels using sparse global structure for label-specific features
Multi-label learning associates a given data instance with one or several class labels.
Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism
tinglyfeng/sentiment_pretraining
•
•
CVPR 2023
Pre-training of deep convolutional neural networks (DCNNs) plays a crucial role in the field of visual sentiment analysis (VSA).
