Abstract
Multi-label classification refers to the supervised learning problem where an instance may be associated with multiple labels. It is well known that exploiting label correlations is important for multi-label learning. Existing approaches typically assume that the distribution of classes is balanced. In many real-world applications, multi-label datasets with imbalanced class distributions occur frequently, which may make various multi-label learning methods ineffective. Since the existing multi-label learning algorithms pay less attention to the problem of correlation with imbalanced label sets, this paper proposed a Multi-Label learning model by exploiting Imbalanced Label Correlations (ML-ILC). ML-ILC uses graph convolution neural network to learn the correlation between labels. At the same time, we suggest that the regularization of minority classes is stronger than that of frequent classes, which can improve the generalization error of minority classes. To investigate the performance of the proposed multi-label learning model, we considered two benchmark datasets including VOC2007 and COCO. The proposed method successfully achieved better classification performance compared to the state-of-the-art compression methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Agrawal, R., Gupta, A., Prabhu, Y., Varma, M.: Multi-label learning with millions of labels: Recommending advertiser bid phrases for web pages, pp. 13–23 (2013)
Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss (2019)
Charte, F., Rivera, A., del Jesus, M.J., Herrera, F.: 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.) HAIS 2013. LNCS (LNAI), vol. 8073, pp. 150–160. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40846-5_16
Chen, S., Chen, Y., Yeh, C., Wang, Y.F.: Order-free rnn with visual attention for multi-label classification. In: AAAI Conference on Artificial Intelligence, pp. 6714–6721 (2018)
Chen, Z., Wei, X., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Conference on Computer Vision and Pattern Recognition, pp. 5172–5181 (2019)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Kao, T.: Advanced parametric mixture model for multi-label text categorization (2006)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations, pp. 1–7 (2017)
Li, L., Wang, H.: Towards label imbalance in multi-label classification with many labels. arXiv (2016)
Li, P., Xie, J., Wang, Q., Gao, Z.: Towards faster training of global covariance pooling networks by iterative matrix square root normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 947–955 (2018)
Lin, T., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740–755 (2014)
Liu, B., Tsoumakas, G.: Making classifier chains resilient to class imbalance. In: Asian Conference on Machine Learning, pp. 280–295. PMLR (2018)
Ma, H., Chen, E., Xu, L., Xiong, H.: Capturing correlations of multiple labels: a generative probabilistic model for multi-label learning. Neurocomputing 92, 116–123 (2012)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing, pp. 1532–1543 (2014)
Read, J., Pfahringer, B., Holmes, G., Frank, E.: Classifier chains for multi-label classification. Mach. Learn. 85(3), 333 (2011)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, pp. 1–8 (2015)
Tsoumakas, G., Zhang, M.: Learning from multi-label data (2009)
Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: Cnn-rnn: a unified framework for multi-label image classification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2285–2294 (2016)
Wang, X., Li, G.Z., Zhang, Q., Huang, D.: Multip-schlo: multi-label protein subchloroplast localization prediction. In: 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 86–89. IEEE (2014)
Wang, Y., Xie, Y., Liu, Y., Zhou, K., Li, X.: Fast graph convolution network based multi-label image recognition via cross-modal fusion. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 1575–1584 (2020)
Wang, Z., Chen, T., Li, G., Xu, R., Lin, L.: Multi-label image recognition by recurrently discovering attentional regions. In: IEEE International Conference on Computer Vision, pp. 464–472 (2017)
Wei, Y., et al.: Hcp: a flexible cnn framework for multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1901–1907 (2016)
Wu, B., Lyu, S., Ghanem, B.: Constrained submodular minimization for missing labels and class imbalance in multi-label learning. In: The Thirtieth AAAI Conference on Artificial Intelligence (AAAI) (2016)
Wu, X.Z., Zhou, Z.H.: A unified view of multi-label performance measures. In: International Conference on Machine Learning, pp. 3780–3788. PMLR (2017)
Wu, Y., Wu, W., Zhang, X., Li, Z., Zhou, M.: Improving recommendation of tail tags for questions in community question answering, pp. 3066–3072 (2016)
Zeng, W., Chen, X., Cheng, H.: Pseudo labels for imbalanced multi-label learning. In: 2014 International Conference on Data Science and Advanced Analytics (DSAA), pp. 25–31. IEEE (2014)
Zhang, J., Wu, Q., Shen, C., Zhang, J., Lu, J.: Multi-label image classification with regional latent semantic dependencies. IEEE Trans. Multimedia 20(10), 2801–2813 (2016)
Zhang, M., Zhou, Z.: A review on multi-label learning algorithms. IEEE Trans. Knowl. Data Eng. 26(8), 1819–1837 (2014)
Zhang, M.L., Li, Y.K., Yang, H., Liu, X.Y.: Towards class-imbalance aware multi-label learning. IEEE Trans. Cybern. 99, 1–13 (2020)
Zhu, F., Li, H., Ouyang, W., Yu, N., Wang, X.: Learning spatial regularization with image-level supervisions for multi-label image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2027–2036 (2017)
Zhu, Z., Chen, H., Hu, Y., Li, J.: Age estimation algorithm of facial images based on multi-label sorting. EURASIP J. Image Video Process. 2018(1), 1–10 (2018). https://doi.org/10.1186/s13640-018-0353-z
Acknowledgments
This work is supported by NSFC under Grant 62076179, and Grant 61732011, Beijing Natural Science Foundation under Grant Z180006, Tianjin Science and Technology Plan Project under Grant 19ZXZNGX00050, Funded by Open Research Fund of the Public Security Behavioral Science Laboratory, People’s Public Security University of China under Grant 2021SYS02.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Gu, S., Yang, L., Li, Y., Li, H. (2021). Multi-label Learning by Exploiting Imbalanced Label Correlations. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13032. Springer, Cham. https://doi.org/10.1007/978-3-030-89363-7_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-89363-7_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89362-0
Online ISBN: 978-3-030-89363-7
eBook Packages: Computer ScienceComputer Science (R0)