research-article

Enhancement of DNN-based multilabel classification by grouping labels based on data imbalance and label correlation

Authors:

Hao LiAuthors Info & Claims

Volume 132, Issue C

https://doi.org/10.1016/j.patcog.2022.108964

Published: 01 December 2022 Publication History

Highlights

•

DNN-based MLC suffers two critical problems: data imbalance and label correlation

•

Neural network configurations with grouped labels were developed to enhance MLC

•

Strategies for grouping labels were proposed to tackle two critical problems in MLC

•

Experiments show that the proposed method increase accuracy of minority labels

•

Adjusting dependence in grouped labels improve accuracy of correlated labels

Abstract

Multilabel classification (MLC) is a challenging task in real-world applications, such as project document classification which led us to conduct this research. In the past decade, deep neural networks (DNNs) have been explored in MLC due to their flexibility in dealing with annotated data. However, DNN-based MLC still suffers many problems. Two critical problems are data imbalance and label correlation. These two problems will become more prominent when a training dataset is limited and with a large label set. In this study, special neural network configurations were developed to enhance the performance of DNN-based MLC based on data imbalance and label correlation. The classification accuracy of minority labels and users-preferred labels was increased using customized label groups. The proposed method was evaluated using river restoration project documents and other fifteen datasets. The results show that the proposed method generally increases f1-score for minority labels up to 10%. Adding label dependence into label groups improves the f1-score of user-preferred majority labels up to 5%. The accuracy increase varies in different datasets.

References

[1]

I. Jerković, A. Kolić, I. Kružić, Š. Anđelinović, Ž. Bašić, Adjusted binary classification (abc) model in forensic science: An example on sex classification from handprint dimensions, Forensic Science International 320 (2021),.

[2]

M.M. Raimundo, T.F. Drumond, A.C.R. Marques, C. Lyra, A. Rocha, F.J. Von Zuben, Exploring multiobjective training in multiclass classification, Neurocomputing 435 (2021) 307–320,.

[3]

Y. Xu, Q. Huang, W.W. Wang, P. Foster, S. Sigtia, P.J.B. Jackson, M.D. Plumbley, Unsupervised feature learning based on deep models for environmental audio tagging, IEEE/ACM Transactions on Audio Speech and Language Processing 25 (6) (2017) 1230–1241,.

Digital Library

[4]

D.M. Salama, N.M. El-Gohary, Semantic text classification for supporting automated compliance checking in construction, Journal of Computing in Civil Engineering 30 (1) (2016) 14,.

[5]

J. Kong, J. Wang, X. Zhang, Hierarchical bert with an adaptive fine-tuning strategy for document classification, Knowledge-Based Systems 238 (2022),.

Digital Library

[6]

A.K. J, A. S, T.E. Trueman, E. Cambria, Comment toxicity detection via a multichannel convolutional bidirectional gated recurrent unit, Neurocomputing 441 (2021) 272–278,.

[7]

F. Mateo, J.J. Garcés-Iniesta, B. Jenninger, J. Gómez-Sanchís, E. Soria-Olivas, P. Chiggiato, Automatic mass spectra recognition for ultra high vacuum systems using multilabel classification, Expert Systems with Applications 178 (2021),.

[8]

Y. Luo, T.L. Liu, D.C. Tao, C. Xu, Multiview matrix completion for multilabel image classification, IEEE Transactions on Image Processing 24 (8) (2015) 2355–2368,.

Digital Library

[9]

F.M. Sun, J.H. Tang, H.J. Li, G.J. Qi, T.S. Huang, Multi-label image categorization with sparse factor representation, IEEE Transactions on Image Processing 23 (3) (2014) 1028–1037,.

Digital Library

[10]

Y. Liu, K. Wen, Q. Gao, X. Gao, F. Nie, Svm based multi-label learning with missing labels for image annotation, Pattern Recognition 78 (2018) 307–317,.

Digital Library

[11]

F. Markatopoulou, V. Mezaris, N. Pittaras, I. Patras, Local features and a two-layer stacking architecture for semantic concept detection in video, Ieee Transactions on Emerging Topics in Computing 3 (2) (2015) 193–204,.

[12]

A. Yadav, D.K. Vishwakarma, A unified framework of deep networks for genre classification using movie trailer, Applied Soft Computing 96 (2020),.

Digital Library

[13]

G. Yu, H. Rangwala, C. Domeniconi, G. Zhang, Z. Yu, Protein function prediction using multilabel ensemble classification, IEEE/ACM Transactions on Computational Biology and Bioinformatics 10 (4) (2013) 1045–1057,.

Digital Library

[14]

Y. Fu, J. Liao, Y. Li, S. Wang, D. Li, X. Li, Multiple perspective attention based on double bilstm for aspect and sentiment pair extract, Neurocomputing 438 (2021) 302–311,.

[15]

A. Omar, T.M. Mahmoud, T. Abd-El-Hafeez, A. Mahfouz, Multi-label arabic text classification in online social networks, Information Systems 100 (2021),.

[16]

Z. Younes, F. Abdallah, T. Denoeux, H. Snoussi, A dependent multilabel classification method derived from the k-nearest neighbor rule, Eurasip Journal on Advances in Signal Processing (2011) 14,.

[17]

W.W. Cheng, E. Hullermeier, Combining instance-based learning and logistic regression for multilabel classification, Machine Learning 76 (2-3) (2009) 211–225,.

Digital Library

[18]

Z.Y. Sun, Y.Y. Zhao, D. Cao, H.W. Hao, Hierarchical multilabel classification with optimal path prediction, Neural Processing Letters 45 (1) (2017) 263–277,.

[19]

H. Huang, H. Liu, Feature selection for hierarchical classification via joint semantic and structural information of labels, Knowledge-Based Systems 195 (2020),.

[20]

N. García-Pedrajas, G. Cerruela-García, Cooperative coevolutionary instance selection for multilabel problems, Knowledge-Based Systems 234 (2021),.

Digital Library

[21]

J. Read, B. Pfahringer, G. Holmes, E. Frank, Classifier chains for multi-label classification, Machine Learning 85 (3) (2011) 333,.

Digital Library

[22]

B. Wang, J. Tsotsos, Dynamic label propagation for semi-supervised multi-class multi-label classification, Pattern Recognition 52 (2016) 75–84,.

Digital Library

[23]

M. Zhang, Z. Zhou, A review on multi-label learning algorithms, Ieee Transactions on Knowledge and Data Engineering 26 (8) (2014) 1819–1837,.

[24]

L. Rokach, A. Schclar, E. Itach, Ensemble methods for multi-label classification, Expert Systems with Applications 41 (16) (2014) 7507–7523,.

Digital Library

[25]

G. Tsoumakas, I. Katakis, I. Vlahavas, Random k-labelsets for multilabel classification, Ieee Transactions on Knowledge and Data Engineering 23 (7) (2011) 1079–1089,.

Digital Library

[26]

S. Abe, Fuzzy support vector machines for multilabel classification, Pattern Recognition 48 (6) (2015) 2110–2117,.

Digital Library

[27]

J.R. Quevedo, O. Luaces, A. Bahamonde, Multi label classifiers with a probabilistic thresholding strategy, Pattern Recognition 45 (2) (2012) 876–883,.

Digital Library

[28]

F. Charte, A.J. Rivera, M.J. del Jesus, F. Herrera, Dealing with difficult minority labels in imbalanced mutilabel data sets, Neurocomputing 326 (2018) 39–53,.

[29]

H.W. Liu, X.L. Li, S.C. Zhang, Learning instance correlation functions for multilabel classification, IEEE Transactions on Cybernetics 47 (2) (2017) 499–510,.

[30]

F. Osayamwen, J. Tapamo, Deep learning class discrimination based on prior probability for human activity recognition, Ieee Access 7 (2019) 14747–14756,.

[31]

M. Bello, G. Nápoles, R. Sánchez, R. Bello, K. Vanhoof, Deep neural network to extract high-level features and labels in multi-label classification problems, Neurocomputing 413 (2020) 259–270,.

[32]

A. Blanco, A. Casillas, A. Pérez, A. Diaz de Ilarraza, Multi-label clinical document classification: Impact of label-density, Expert Systems with Applications 138 (2019),.

[33]

O. AlDhafer, I. Ahmad, S. Mahmood, An end-to-end deep learning system for requirements classification using recurrent neural networks, Information and Software Technology 147 (2022),.

Digital Library

[34]

S. Qin, H. Wu, R. Nie, J. He, Deep model with neighborhood-awareness for text tagging, Knowledge-Based Systems 196 (2020),.

[35]

E.d.O. Andrade, J. Viterbo, C.N. Vasconcelos, J. Guérin, F.C. Bernardini, A model based on lstm neural networks to identify five different types of malware, Procedia Computer Science 159 (2019) 182–191,.

Digital Library

[36]

J.A. Kumar, T.E. Trueman, E. Cambria, Gender-based multi-aspect sentiment detection using multilabel learning, Information Sciences 606 (2022) 453–468,.

Digital Library

[37]

L. Chen, Y. Wang, S. Mo, Automatic labeling of river restoration project documents based on project objectives and restoration methods, Expert Systems with Applications 197 (2022),.

Digital Library

[38]

P. Davis, F. Aziz, M.T. Newaz, W. Sher, L. Simon, The classification of construction waste material using a deep convolutional neural network, Automation in Construction 122 (2021),.

[39]

M. Budka, A.W.U. Ashraf, M. Bennett, S. Neville, A. Mackrill, Deep multilabel cnn for forensic footwear impression descriptor identification, Applied Soft Computing 109 (2021),.

Digital Library

[40]

W. Bi, J. Kwok, Efficient multi-label classification with many labels, in: Proceedings of the 30th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2013.

[41]

R. Rastogi, S. Mortaza, Multi-label classification with missing labels using label correlation and robust structural learning, Knowledge-Based Systems (2021) 107336. https://doi.org/10.1016/j.knosys.2021.107336.

[42]

M.M. Bittencourt, R.M. Silva, T.A. Almeida, Ml-mdltext: An efficient and lightweight multilabel text classifier with incremental learning, Applied Soft Computing 96 (2020),.

Digital Library

[43]

F. Charte, A. Rivera, M.J. del Jesus, F. Herrera, A first approach to deal with imbalance in multi-label datasets, in: Pan J.-S., Polycarpou M.M., Woźniak M., de Carvalho A.C.P.L.F., Quintián H., Corchado E. (Eds.), Hybrid Artificial Intelligent Systems, Springer Berlin Heidelberg, Berlin, Heidelberg, 2013, pp. 150–160.

[44]

F. Charte, A.J. Rivera, M.J. del Jesus, F. Herrera, Dealing with difficult minority labels in imbalanced mutilabel data sets, Neurocomputing 326-327 (2019) 39–53,.

[45]

F. Charte, A.J. Rivera, M.J. del Jesus, F. Herrera, Remedial-hwr: Tackling multilabel imbalance through label decoupling and data resampling hybridization, Neurocomputing 326-327 (2019) 110–122,.

[46]

Z.-F. He, M. Yang, Y. Gao, H.-D. Liu, Y. Yin, Joint multi-label classification and label correlations with missing labels and feature selection, Knowledge-Based Systems 163 (2019) 145-158. https://doi.org/10.1016/j.knosys.2018.08.018.

[47]

K. Daisey, S.D. Brown, Effects of the hierarchy in hierarchical, multi-label classification, Chemometrics and Intelligent Laboratory Systems 207 (2020),.

[48]

S. Wang, J. Wang, Z. Wang, Q. Ji, Enhancing multi-label classification by modeling dependencies among labels, Pattern Recognition 47 (10) (2014) 3405–3413,.

[49]

J. Huang, G. Li, S. Wang, Z. Xue, Q. Huang, Multi-label classification by exploiting local positive and negative pairwise label correlation, Neurocomputing 257 (2017) 164–174,.

[50]

G. Chen, Y. Song, F. Wang, C. Zhang, Semi-supervised multi-label learning by solving a sylvester equation, in: Proceedings of the 2008 siam international conference on data mining (sdm), Society for Industrial and Applied Mathematics, 2008, pp. 410–419,.

[51]

M.L. McHugh, The chi-square test of independence, Biochem Med (Zagreb) 23 (2) (2013) 143–149,.

[52]

Riverwiki, Website: https://restorerivers.eu, (2019) (Accessed date: 2020.09.20)

[53]

T. Mikolov, I. Sutskever, K. Chen, G.S. Corrado, J. Dean, Distributed representations of words and phrases and their compositionality, Advances in neural information processing systems (2013) 3111–3119.

[54]

T. Grigorios, S.-X. Eleftherios, V. Jozef, V. Ioannis, Mulan: A java library for multi-label learning, Journal of Machine Learning Research 12 (71) (2011) 2411–2414.

Cited By

Chen LJiang XWang Y(2024)A Bayesian network learning method for sparse and unbalanced data with GNN-based multilabel classification applicationApplied Soft Computing10.1016/j.asoc.2024.111393154:COnline publication date: 1-Mar-2024
https://dl.acm.org/doi/10.1016/j.asoc.2024.111393

Index Terms

Enhancement of DNN-based multilabel classification by grouping labels based on data imbalance and label correlation
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning approaches
      1. Classification and regression trees
      2. Neural networks
2. Information systems

Index terms have been assigned to the content through auto-classification.

Recommendations

Semi-supervised multi-label classification using incomplete label information
Highlights
- An inductive semi-supervised method called Smile is proposed for multi-label classification using incomplete label information.
Abstract
Classifying multi-label instances using incompletely labeled instances is one of the fundamental tasks in multi-label learning. Most existing methods regard this task as supervised weak-label learning problem and assume sufficient ...
Multi-label classification with weak labels by learning label correlation and label regularization
Abstract
In conventional multi-label learning, each training instance is associated with multiple available labels. Nevertheless, real-world objects usually exhibit more sophisticated properties such as abundant irrelevant features, incomplete labels, ...
Transductive Multilabel Learning via Label Set Propagation

The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Pattern Recognition

Pattern Recognition Volume 132, Issue C

Dec 2022

829 pages

ISSN:0031-3203

Issue’s Table of Contents

Copyright © 2022.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 December 2022

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 30 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Chen LJiang XWang Y(2024)A Bayesian network learning method for sparse and unbalanced data with GNN-based multilabel classification applicationApplied Soft Computing10.1016/j.asoc.2024.111393154:COnline publication date: 1-Mar-2024
https://dl.acm.org/doi/10.1016/j.asoc.2024.111393

View Options

View options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents