Abstract
A Bayesian framework is proposed to define flexible coupling models for joint decompositions of data sets. Under this framework, a solution to the joint decomposition can be cast in terms of a maximum a posteriori estimator. Examples of joint posterior distributions are provided, including general Gaussian priors and non Gaussian coupling priors. Then simulations are reported and show the effectiveness of this approach to fuse information from data sets, which are inherently of different size due to different time resolution of the measurement devices.
R.C. Farias—This research was supported in part by the ERC Grants AdG-2013-320594 “DECODA” (R. Cabral Farias, J. E. Cohen and P. Comon) and AdG-2012-320684 “CHESS” (Christian Jutten). This paper is a short version of a report available online at: https://hal.archives-ouvertes.fr/hal-01135920/.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We could also consider a minimum mean squared error setting but then we would need to evaluate \(p(\varvec{\mathcal {Y}},\varvec{\mathcal {Y}}')\), which is normally cumbersome.
References
Acar, E., Kolda, T.G., Dunlavy, D.M.: All-at-once optimization for coupled matrix and tensor factorizations. arXiv preprint arXiv:1105.3422 (2011)
Acar, E., Lawaetz, A.J., Rasmussen, M.A., Bro, R.: Structure-revealing data fusion model with applications in metabolomics. In: Conference Proceedings of the IEEE Engineering in Medicine and Biology Society, pp. 6023–6026. IEEE (2013)
Acar, E., Rasmussen, M.A., Savorani, F., Næs, T., Bro, R.: Understanding data fusion within the framework of coupled matrix and tensor factorizations. Chemometr. Intell. Lab. 129, 53–63 (2013)
Aldroubi, A., Gröchenig, K.: Nonuniform sampling and reconstruction in shift-invariant spaces. SIAM Rev. 43(4), 585–620 (2001)
Banerjee, A., Basu, S., Merugu, S.: Multi-way clustering on relation graphs. In: SDM, vol. 7, pp. 225–334. SIAM (2007)
Cabral Farias, R., Cohen, J.E., Comon, P.: Exploring multimodal data fusion through joint decompositions with flexible couplings. arXiv preprint arXiv:1505.07717 (2015)
Comon, P., Luciani, X., De Almeida, A.L.F.: Tensor decompositions, alternating least squares and other tales. J. Chemometr. 23(7–8), 393–405 (2009)
Ermiş, B., Acar, E., Cemgil, A.T.: Link prediction via generalized coupled tensor factorisation. arXiv preprint arXiv:1208.6231 (2012)
Harshman, R.A., Lundy, M.E.: Data preprocessing and the extended PARAFAC model, pp. 216–284. Research Methods for Multimode Data Analysis (1984)
Jørgensen, B.: The theory of exponential dispersion models and analysis of deviance. Number 51 in Monografias de matematica. CNPQ, IMPA (Brazil) (1992)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Lin, Y.-R., Sun, J., Castro, P., Konuru, R., Sundaram, H., Kelliher, A.: Metafac: community discovery via relational hypergraph factorization. In: Proceedings of the ACM SIGKDD Conference, pp. 527–536. ACM (2009)
Margolis, E., Eldar, Y.C.: Nonuniform sampling of periodic bandlimited signals. IEEE Trans. Sig. Process. 56(7), 2728–2745 (2008)
Seichepine, N., Essid, S., Fevotte, C., Cappé, O.: Soft nonnegative matrix co-factorization. IEEE Trans. Sig. Process. 62(22), 5940–5949 (2014)
Singh, A.P., Gordon, G.J.: Relational learning via collective matrix factorization. In: Proceedings of the 14th ACM SIGKDD Conference, pp. 650–658. ACM (2008)
Sorber, L., Van Barel, M., De Lathauwer, L.: Structured data fusion.Technical report, KU Leuven (Belgium), pp. 13–177 (2013)
Sørensen, M., Domanov, I., Nion, D., De Lathauwer, L.: Coupled canonical polyadic decompositions and (coupled) decompositions in multilinear rank-(\({\rm {L_{r, n}}, {L_{r, n}}}, 1\)) terms. Technical report, KU Leuven (Belgium) (2013)
Sui, J., Adali, T., Yu, Q., Chen, J., Calhoun, V.D.: A review of multivariate methods for multimodal fusion of brain imaging data. J. Neurosci. Meth. 204(1), 68–81 (2012)
Yılmaz, K.Y., Cemgil, A.T., Simsekli, U.: Generalised coupled tensor factorisation. In: Advances Neural Information Processing Systems, pp. 2151–2159 (2011)
Yilmaz, Y.K., Cemgil, A.T.: Alpha/beta divergences and tweedie models. arXiv preprint arXiv:1209.4280 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Cabral Farias, R., Cohen, J.E., Jutten, C., Comon, P. (2015). Joint Decompositions with Flexible Couplings. In: Vincent, E., Yeredor, A., Koldovský, Z., Tichavský, P. (eds) Latent Variable Analysis and Signal Separation. LVA/ICA 2015. Lecture Notes in Computer Science(), vol 9237. Springer, Cham. https://doi.org/10.1007/978-3-319-22482-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-22482-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-22481-7
Online ISBN: 978-3-319-22482-4
eBook Packages: Computer ScienceComputer Science (R0)