Abstract
Multi-view learning attempts to generate a model with a better performance by exploiting information among multi-view data. Most existing approaches only focus on either consistency or complementarity principle, and learn representations (or features) of the multi-view data. In this paper, to utilize both complementarity and consistency simultaneously, and explore the potential of deep learning in multi-view learning, we propose a novel supervised multi-view learning algorithm, called multi-view capsule network (MVCapsNet), which extracts a feature matrix of all views by a group of encoders, and obtains a classification matrix fusing common and special information of multiple views. Extensive experiments conducted on eight real-world datasets have demonstrated the effectiveness of our proposed method, and show its superiority over several state-of-the-art baseline methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT, pp. 92–100. ACM, New York (1998). https://doi.org/10.1145/279943.279962
Cai, D., He, X., Han, J., Huang, T.S.: Graph regularized nonnegative matrix factorization for data representation. TPAMI 33(8), 1548–1560 (2011). https://doi.org/10.1109/TPAMI.2010.231
Shao, J., et al.: Common and distinct changes of default mode and salience network in schizophrenia and major depression. Brain Imaging Behav. 12(6), 1708–1719 (2018). https://doi.org/10.1007/s11682-018-9838-8
Sun, S.: A survey of multi-view machine learning. Neural Comput. Appl. 23(7–8), 2031–2038 (2013). https://doi.org/10.1007/s00521-013-1362-6
Li, Y., Yang, M., Zhang, Z.: A Survey of Multi-View Representation Learning. arXiv preprint arXiv:1610.01206 (2016). https://doi.org/10.1109/tkde.2018.2872063
Xu, C., Tao, D., Xu, C.: A survey on multi-view learning. arXiv preprint arXiv:1304.5634 (2013). https://doi.org/10.1145/3065386
Chao, G., Sun, S., Bi, J.: A Survey on Multi-View Clustering. arXiv preprint arXiv:1712.06246 (2017)
Chaudhuri, K., Kakade, S.M., Livescu, K.: Multi-view clustering via canonical correlation analysis. In: ICML, pp. 129–136. ACM, New York (2009). https://doi.org/10.1145/1553374.1553391
Kursun, O., Alpaydin, E.: Canonical correlation analysis for multiview semisupervised feature extraction. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010. LNCS (LNAI), vol. 6113, pp. 430–436. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13208-7_54
Sharma, A., Kumar, A., Daume, H., Jacobs, D.W.: Generalized multi-view analysis: a discriminative latent space. In: CVPR, pp. 2160–2167. IEEE, Piscataway (2012). https://doi.org/10.1145/3065386
Nie, F., Li, J., Li, X.: Parameter-free auto-weighted multiple graph learning: a framework for multiview clustering and semi-supervised classification. In: IJCAI, pp. 1881–1887. AAAI, Menlo Park (2016)
Liu, J., Jiang, Y., Li, Z.: Partially shared latent factor learning with multiview data. IEEE Trans. Neural Networks Learn. Syst. 29(8), 1233–1246 (2015). https://doi.org/10.1109/TNNLS.2014.2335234
Zhang, Z., Qin, Z., Li, P., Yang, Q., Shao, J.: Multi-view discriminative learning via joint non-negative matrix factorization. In: Pei, J., Manolopoulos, Y., Sadiq, S., Li, J. (eds.) DASFAA 2018. LNCS, vol. 10828, pp. 542–557. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91458-9_33
Singh, A.P., Gordon, G.J.: Relational learning via collective matrix factorization. In: KDD, pp. 650–658. ACM, New York (2008). https://doi.org/10.1145/1401890.1401969
Gao, J., Han, J., Liu, J., Wang, C.: Multi-view clustering via joint nonnegative matrix factorization. In: SDM, pp. 252–260. SIAM, Philadelphia (2013). https://doi.org/10.1137/1.9781611972832.28
Lee, D.D., Seung, H.S.: Learning the parts of objects by nonnegative matrix factorization. Nature 401, 788–791 (1999). https://doi.org/10.1038/44565
Sabour, S., Frosst, N., Hinton, G.E.: Dynamic Routing Between Capsules. In: NIPS, pp. 3859–3869. Curran Associates, New York (2017). https://doi.org/10.1167/8.7.34
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS, pp. 249–256. MIT, Cambridge (2010). 10.1.1.207.2059
Wang, Z., Kong, X., Fu, H.: Feature extraction via multi-view non-negative matrix factorization with local graph regularization. In: ICIP, pp. 3500–3504. IEEE, Piscataway (2015). https://doi.org/10.1109/icip.2015.7351455
Wang, H., Yang, Y., Li, T.: Multi-view clustering via concept factorization with local manifold regularization. In: ICDM, pp. 1245–1250. IEEE, Piscataway (2016). https://doi.org/10.1109/icdm.2016.0167
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135. MIT, Cambridge (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Jw., Ding, Xh., Lu, Rk., Lian, Yf., Wang, Dz., Luo, Xl. (2019). Multi-View Capsule Network. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation. ICANN 2019. Lecture Notes in Computer Science(), vol 11727. Springer, Cham. https://doi.org/10.1007/978-3-030-30487-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-30487-4_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30486-7
Online ISBN: 978-3-030-30487-4
eBook Packages: Computer ScienceComputer Science (R0)