Abstract
Recently, many applications tend to find common and distinctive features from a group of datasets, of which distributions and structures are generally various. However, most existing methods can just cope with specific problems with fixed distributions and structures. In this paper, a more flexible framework for multi-block data learning is proposed. There are mainly two advantages compared with previous methods: (a) the proposed method can extract global common, local common, and distinctive features automatically; (b) various distributed datasets can be processed simultaneously as long as distributions are in exponential family. The results of numerical experiments demonstrate that the proposed method outperforms conventional methods for recommendation system problems.
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
Mitchell, T.M., et al.: Predicting human brain activity associated with the meanings of nouns. Science 320(5880), 1191–1195 (2008)
Nickel, M.: Tensor factorization for relational learning. Diss. lmu (2013)
Chen, C.-Y., Grauman, K.: Inferring unseen views of people (2014)
Zhou, G., Cichocki, A., Xie, S.: Common and individual features analysis: beyond canonical correlation analysis, Arxiv preprint (2012)
Nelder, J.A., Baker, R.J.: Generalized linear models. Encyclopedia of Statistical Sciences (1972)
Collins, M., Dasgupta, S., Schapire, R.E.: A generalization of principal components analysis to the exponential family. In: Advances in Neural Information Processing Systems (2001)
Singh, A.P., Gordon, G.J.: Relational learning via collective matrix factorization. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM (2008)
Bouchard, G., Yin, D., Guo, S.: Convex collective matrix factorization. In: Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics (2013)
Lfstedt, T., Hoffman, D., Trygg, J.: Global, local and unique decompositions in OnPLS for multiblock data analysis. Anal. Chim. Acta 791, 13–24 (2013)
Aroian, L.A.: The probability function of the product of two normally distributed variables. Ann. Math. Stat. 18, 265–271 (1947)
Zhao, Q., Zhang, L., Cichocki, A.: Bayesian CP factorization of incomplete tensors with automatic rank determination. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1751–1763 (2015)
Acar, E., Dunlavy, D.M., Kolda, T.G.: A scalable optimization approach for fitting canonical tensor decompositions. J. Chemometr. 25(2), 67–86 (2011)
Rennie, J.D.M., Srebro, N.: Fast maximum margin matrix factorization for collaborative prediction. In: Proceedings of the 22nd International Conference on Machine Learning. ACM (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, C., Guo, L., Dou, Z., Si, G., Li, C. (2017). Generalized Multi-linear Mixed Effects Model. In: Park, J., Pan, Y., Yi, G., Loia, V. (eds) Advances in Computer Science and Ubiquitous Computing. UCAWSN CUTE CSA 2016 2016 2016. Lecture Notes in Electrical Engineering, vol 421. Springer, Singapore. https://doi.org/10.1007/978-981-10-3023-9_41
Download citation
DOI: https://doi.org/10.1007/978-981-10-3023-9_41
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3022-2
Online ISBN: 978-981-10-3023-9
eBook Packages: EngineeringEngineering (R0)