Abstract
In multi-label learning, learning specific features for each label is an effective strategy, and most of the existing multi-label classification methods based on label-specific features commonly use the original feature space to learn specific features for each label directly. Due to the problem of dimensionality disaster in the feature space, it may not be the optimal strategy to directly generate the specific feature of the label in the original feature space. Therefore, this paper proposes a multi-label learning framework that joins neural networks and label-specific features. First, the neural network projects the original feature space to a low-dimensional mapping space to learn potential low-dimensional feature space representations, and this nonlinear feature mapping can mine the potential feature information inside the complex feature space. Then, in the low-dimensional mapping space, specific features of the labels are learned using empirical minimization loss. Finally, a unified multi-label classification model is constructed by considering label correlation and instance similarity issues. Extensive experiments are conducted on 12 different multi-label data sets and demonstrate the better generalizability of our proposed approaches.
Similar content being viewed by others
References
Gargiulo F, Silvestri S, Ciampi M, De Pietro G (2019) Deep neural network for hierarchical extreme multi-label text classification. Appl Soft Comput 79:125–138
Li Y, Song Y, Luo J (2017) Improving pairwise ranking for multi-label image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3617–3625
Wen S, Liu W, Yang Y, Zhou P, Guo Z, Yan Z, Chen Y, Huang T (2020) Multilabel image classification via feature/label co-projection. IEEE Trans Syst Man Cybern Syst 51:7250–7259
Gull S, Shamim N, Minhas F (2019) Amap: hierarchical multi-label prediction of biologically active and antimicrobial peptides. Comput Biol Med 107:172–181
Liu L, Tang L, Jin X, Zhou W (2019) A multi-label supervised topic model conditioned on arbitrary features for gene function prediction. Genes 10(1):57
Zhang M-L, Zhou Z-H (2013) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837
Boutell MR, Luo J, Shen X, Brown CM (2004) Learning multi-label scene classification. Pattern Recogn 37(9):1757–1771
Zhang M-L, Zhou Z-H (2007) Ml-knn: a lazy learning approach to multi-label learning. Pattern Recogn 40(7):2038–2048
Gong C, Tao D, Yang J, Liu W (2016) Teaching-to-learn and learning-to-teach for multi-label propagation. In: Proceedings of the AAAI conference on artificial intelligence, vol 30
Weng W, Lin Y, Shunxiang W, Li Y, Kang Y (2018) Multi-label learning based on label-specific features and local pairwise label correlation. Neurocomputing 273:385–394
Read J, Pfahringer B, Holmes G, Frank E (2011) Classifier chains for multi-label classification. Mach Learn 85(3):333–359
Zhao W, Kong S, Bai J, Fink D, Gomes C (2021) Learning high-order label correlation for multi-label classification via attention-based variational autoencoders. arXiv preprint arXiv:2103.06375
Guo B, Hou C, Nie F, Yi D (2016) Pervised multi-label dimensionality reduction. In: 2016 IEEE 16th international conference on data mining (ICDM. IEEE), pp 919–924
Øyvind MK, Cristina S-R, Maria BF, Robert J (2019) Noisy multi-label semi-supervised dimensionality reduction. Pattern Recogn 90:257–270
Zhang M-L, Lei W (2014) Lift: multi-label learning with label-specific features. IEEE Trans Pattern Anal Mach Intell 37(1):107–120
Huang J, Li G, Huang Q, Wu X (2015) Learning label specific features for multi-label classification. In: 2015 IEEE international conference on data mining. IEEE, pp 181–190
Huang J, Li G, Huang Q, Xindong W (2017) Joint feature selection and classification for multilabel learning. IEEE Trans Cybern 48(3):876–889
Zhang M-L, Zhou Z-H (2006) Multilabel neural networks with applications to functional genomics and text categorization. IEEE Trans Knowl Data Eng 18(10):1338–1351
Bello M, Nápoles G, Sánchez R, Bello R, Vanhoof K (2020) Deep neural network to extract high-level features and labels in multi-label classification problems. Neurocomputing 413:259–270
Nam J, Kim J, Mencía EL, Gurevych I, Furnkranz J (2014) Large-scale multi-label text classification–revisiting neural networks. Joint European conference on machine learning and knowledge discovery in databases. Springer, Berlin, pp 437–452
Weizhi Liao Yu, Wang YY, Zhang X, Ma P (2020) Improved sequence generation model for multi-label classification via cnn and initialized fully connection. Neurocomputing 382:188–195
Wang J, Yang Y, Mao J, Huang Z, Huang C, Xu W (2016) Cnn-rnn: a unified framework for multi-label image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2285–2294
Zhang M-L (2009) M l-rbf: Rbf neural networks for multi-label learning. Neural Process Lett 29(2):61–74
Huimin L, Zhang M, Xing X, Li Y, Shen HT (2020) Deep fuzzy hashing network for efficient image retrieval. IEEE Trans Fuzzy Syst 29(1):166–176
Xie Y, Zhang J, Xia Y, Shen C (2020) A mutual bootstrapping model for automated skin lesion segmentation and classification. IEEE Trans Med Imaging 39(7):2482–2493
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Cheng Y, Zhao D, Wang Y, Pei G (2019) Multi-label learning with kernel extreme learning machine autoencoder. Knowl-Based Syst 178:1–10
Parwez MA, Abulaish M et al (2019) Multi-label classification of microblogging texts using convolution neural network. IEEE Access 7:68678–68691
Zhu J, Liao S, Lei Z, Li SZ (2017) Multi-label convolutional neural network based pedestrian attribute classification. Image Vis Comput 58:224–229
Nam J, Mencía EL, Kim HJ, Fürnkranz J (2017) Maximizing subset accuracy with recurrent neural networks in multi-label classification. In: Proceedings of the 31st international conference on neural information processing systems, pp 5419–5429
Chen SF, Chen YC, Yeh CK, Wang YCF (2018) Order-free rnn with visual attention for multi-label classification. In: Thirty-Second AAAI conference on artificial intelligence
Rui H, Liuyue K (2021) Local positive and negative label correlation analysis with label awareness for multi-label classification. Int J Mach Learn Cybern 12:1–14
Bidgoli AA, Ebrahimpour-komleh H, Rahnamayan S (2021) A novel binary many-objective feature selection algorithm for multi-label data classification. Int J Mach Learn Cybern 12(7):2041–2057
Huang J, Qin F, Zheng X, Cheng Z, Yuan Z, Zhang W, Huang Q (2019) Improving multi-label classification with missing labels by learning label-specific features. Inf Sci 492:124–146
Zhu W, Li W, Jia X (2020) Multi-label learning with local similarity of samples. In: 2020 International joint conference on neural networks (IJCNN). IEEE, pp 1–8
Zhu Y, Kwok JT, Zhou Z-H (2017) Multi-label learning with global and local label correlation. IEEE Trans Knowl Data Eng 30(6):1081–1094
Jie B, Zhang D, Cheng B, Shen D, Initiative ADN (2015) Manifold regularized multitask feature learning for multimodality disease classification. Hum Brain Mapp 36(2):489–507
Han H, Mengxing Huang Yu, Zhang XY, Feng W (2019) Multi-label learning with label specific features using correlation information. IEEE Access 7:11474–11484
Gersho A, Gray RM (2012) Vector quantization and signal compression, vol 159. Springer, Berlin
Abdel-Ghaffar KAS (2019) Sets of binary sequences with small total hamming distances. Inf Process Lett 142:27–29
Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imag Sci 2(1):183–202
Lin Z, Ganesh A, Wright J, Wu L, Chen M, Ma Y (2009) Fast convex optimization algorithms for exact recovery of a corrupted low-rank matrix. Coordinated Science Laboratory Report no. UILU-ENG-09-2214, DC-246
Wang Y, Zheng W, Cheng Y, Zhao D (2020) Joint label completion and label-specific features for multi-label learning algorithm. Soft Comput 24(9):6553–6569
Tan Y, Sun D, Shi Y, Gao L, Gao Q, Lu Y (2021) Bi-directional mapping for multi-label learning of label-specific features. Appl Intell 52:1–20
Acknowledgements
This work is supported by the National Natural Science Foundation of China (no. 62071001), the Anhui Natural Science Foundation of China (nos. 2008085MF192 and 2008085MF183), the Key Science Project of Anhui Education Department of China (nos. KJ2018A0012, KJ2019A0023, and KJ2019A0022), and the CERNET Innovation Project of China (nos. NGII20180612, NGII20180312, and NGII20180624).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jia, L., Sun, D., Shi, Y. et al. Learning label-specific features via neural network for multi-label classification. Int. J. Mach. Learn. & Cyber. 14, 1161–1177 (2023). https://doi.org/10.1007/s13042-022-01692-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01692-7