Improved Coupled Tensor Factorization with Its Applications in Health Data Analysis

Coupled matrix and tensor factorizations have been successfully used in many data fusion scenarios where datasets are assumed to be exactly coupled. However, in the real world, not all the datasets share the same factor matrices, which makes joint analysis of multiple heterogeneous sources challenging. For this reason, approximate coupling or partial coupling is widely used in real-world data fusion, with exact coupling as a special case of these techniques. However, to fully address the challenge of tensor factorization, in this paper, we propose two improved coupled tensor factorization methods: one for approximately coupled datasets and the other for partially coupled datasets. A series of experiments using both simulated data and three real-world datasets demonstrate the improved accuracy of these approaches over existing baselines. In particular, when experiments on MRI data is conducted, the performance of our method is improved even by 12.47% in terms of accuracy compared with traditional methods.

[1]  Lieven De Lathauwer,et al.  Coupled matrix-tensor factorizations — The case of partially shared factors , 2017, 2017 51st Asilomar Conference on Signals, Systems, and Computers.

[2]  J. Kruskal.  Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics , 1977 .

[3]  Geoffrey J. Gordon,et al.  Relational learning via collective matrix factorization , 2008, KDD.

[4]  Wei Liu,et al.  ASTEN: An accurate and scalable approach to Coupled Tensor Factorization , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[5]  Martin Haardt,et al.  Analysis of the photic driving effect via joint EEG and MEG data processing based on the coupled CP decomposition , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[6]  Xun Chen,et al.  Underdetermined Joint Blind Source Separation of Multiple Datasets , 2017, IEEE Access.

[7]  Rasmus Bro,et al.  Understanding data fusion within the framework of coupled matrix and tensor factorizations , 2013 .

[8]  Jin Fan,et al.  CTF-PSF: Coupled Tensor Factorization with Partially Shared Factors , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[9]  Nikos D. Sidiropoulos,et al.  Turbo-SMT: Accelerating Coupled Sparse Matrix-Tensor Factorizations by 200x , 2014, SDM.

[10]  Ali Taylan Cemgil,et al.  Link Prediction via Generalized Coupled Tensor Factorisation , 2012, ArXiv.

[11]  Fang Chen,et al.  Discovering Both Explicit and Implicit Similarities for Cross-Domain Recommendation , 2017, PAKDD.

[12]  Michael R. Lyu,et al.  SoRec: social recommendation using probabilistic matrix factorization , 2008, CIKM '08.

[13]  Jiayu Zhou,et al.  Who, What, When, and Where: Multi-Dimensional Collaborative Recommendations Using Tensor Factorization on Sparse User-Generated Data , 2015, WWW.

[14]  Tamara G. Kolda,et al.  All-at-once Optimization for Coupled Matrix and Tensor Factorizations , 2011, ArXiv.

[15]  Wim Van Paesschen,et al.  Fusion of electroencephalography and functional magnetic resonance imaging to explore epileptic network activity , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[16]  Nikos D. Sidiropoulos,et al.  Scoup-SMT: Scalable Coupled Sparse Matrix-Tensor Factorization , 2013, ArXiv.

[17]  Xing Xie,et al.  Collaborative Filtering Meets Mobile Recommendation: A User-Centered Approach , 2010, AAAI.

[18]  Fei Wang,et al.  Social contextual recommendation , 2012, CIKM.

[19]  Liviu Badea,et al.  Extracting Gene Expression Profiles Common to Colon and Pancreatic Adenocarcinoma Using Simultaneous Nonnegative Matrix Factorization , 2007, Pacific Symposium on Biocomputing.

[20]  Rasmus Bro,et al.  Structure-revealing data fusion , 2014, BMC Bioinformatics.

[21]  Rasmus Bro,et al.  A new approach for modelling sensor based data , 2005 .

[22]  Nikos D. Sidiropoulos,et al.  Tensors for Data Mining and Data Fusion , 2016, ACM Trans. Intell. Syst. Technol..

[23]  Arie Yeredor,et al.  Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation , 2002, IEEE Trans. Signal Process..

[24]  Rasmus Bro,et al.  Structure-revealing data fusion model with applications in metabolomics , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[25]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[26]  Bin Liu,et al.  Integrating supply and demand chains in personalized recommendation via chain-coupled tensor factorization , 2017, 2017 IEEE 21st International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[27]  Vince D. Calhoun,et al.  Tensor-based fusion of EEG and FMRI to understand neurological changes in schizophrenia , 2016, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[28]  Tamara G. Kolda,et al.  Scalable Tensor Factorizations for Incomplete Data , 2010, ArXiv.

[29]  Christian Jutten,et al.  Multimodal Data Fusion: An Overview of Methods, Challenges, and Prospects , 2015, Proceedings of the IEEE.

[30]  Andrzej Cichocki,et al.  Linked Component Analysis From Matrices to High-Order Tensors: Applications to Biomedical Data , 2015, Proceedings of the IEEE.

[31]  Rasmus Bro,et al.  Data Fusion in Metabolomics Using Coupled Matrix and Tensor Factorizations , 2015, Proceedings of the IEEE.

[32]  Vince D. Calhoun,et al.  ACMTF for fusion of multi-modal neuroimaging data and identification of biomarkers , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[33]  Orly Alter,et al.  GSVD Comparison of Patient-Matched Normal and Tumor aCGH Profiles Reveals Global Copy-Number Alterations Predicting Glioblastoma Multiforme Survival , 2012, PloS one.