Multi-Label Learning

81 papers with code • 1 benchmarks • 7 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:

  1. Kumar, S., Rastogi, R., Low rank label subspace transformation for multi-label learning with missing labels. Information Sciences 596, 53–72 (2022)

  2. Zhang M-L, Zhou Z-H (2013) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837

  3. Gibaja E, Ventura S (2015) A tutorial on multilabel learning. ACM Comput Surveys (CSUR) 47(3):1–38

  4. 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

  5. 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

  6. Chen Z, Ren J (2021) Multi-label text classification with latent word-wise label information. Appl Intell 51(2):966–979

Most implemented papers

Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding

zhoubolei/moments_models 1 Nov 2019

Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds.

Multi-Label Learning from Single Positive Labels

elijahcole/single-positive-multi-label CVPR 2021

When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image.

Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

xinyu1205/robust-loss-mlml 13 Dec 2021

Multi-label learning in the presence of missing labels (MLML) is a challenging problem.

Incomplete Multi-View Weak-Label Learning with Noisy Features and Imbalanced Labels

mtics/nail 4 Jan 2022

A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views.

DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification

justsmart/DICNet 15 Mar 2023

To deal with the double incomplete multi-view multi-label classification problem, we propose a deep instance-level contrastive network, namely DICNet.

LIFT : Multi-Label Learning with Label-Specific Features

Prady029/LIFT-MultiLabel-Learning-with-Label-Specific-Features International Joint Conferences on Artificial Intelligence 2014

Existing approaches learn from multi-label data by manipulating with identical feature set, i. e. the very instance representation of each example is employed in the discrimination processes of all class labels.

A hybrid algorithm for Bayesian network structure learning with application to multi-label learning

madbix/bnlearn-clone-3.4 18 Jun 2015

Our extensive experiments show that H2PC outperforms MMHC in terms of goodness of fit to new data and quality of the network structure with respect to the true dependence structure of the data.

Cost-Sensitive Reference Pair Encoding for Multi-Label Learning

yangarbiter/multilabel-learn 29 Nov 2016

Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing.

Semi-supervised multi-label feature selection via label correlation analysis with l1-norm graph embedding

x-d-wang/x-d-wang.github.io Image and Vision Computing 2017

Compared with the previous works, there are two advantages of our algorithm: (1) Manifold learning which leverages the underlying geometric structure of the training data is imposed to utilize both labeled and unlabeled data.