@InProceedings{6952001,
  author = {E. Acar and M. Nilsson and M. Saunders},
  booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
  title = {A flexible modeling framework for coupled matrix and tensor factorizations},
  year = {2014},
  pages = {111-115},
  abstract = {Joint analysis of data from multiple sources has proved useful in many disciplines including metabolomics and social network analysis. However, data fusion remains a challenging task in need of data mining tools that can capture the underlying structures from multi-relational and heterogeneous data sources. In order to address this challenge, data fusion has been formulated as a coupled matrix and tensor factorization (CMTF) problem. Coupled factorization problems have commonly been solved using alternating methods and, recently, unconstrained all-at-once optimization algorithms. In this paper, unlike previous studies, in order to have a flexible modeling framework, we use a general-purpose optimization solver that solves for all factor matrices simultaneously and is capable of handling additional linear/nonlinear constraints with a nonlinear objective function. We formulate CMTF as a constrained optimization problem and develop accurate models more robust to overfactoring. The effectiveness of the proposed modeling/algorithmic framework is demonstrated on simulated and real data.},
  keywords = {data mining;matrix decomposition;optimisation;sensor fusion;tensors;coupled matrix and tensor factorization problem;flexible modeling framework;data fusion;CMTF problem;general-purpose optimization solver;constrained optimization problem;all factor matrices;nonlinear objective function;unconstrained all-at-once optimization algorithms;Tensile stress;Data models;Optimization;Data integration;Nuclear magnetic resonance;Chemicals;Joints;data fusion;tensor factorizations;nonlinear optimization;nonlinear constraints;SNOPT},
  issn = {2076-1465},
  month = {Sep.},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569911163.pdf},
}

{"_id":"Dtc3yDuvvqfPNZo9L","bibbaseid":"acar-nilsson-saunders-aflexiblemodelingframeworkforcoupledmatrixandtensorfactorizations-2014","authorIDs":[],"author_short":["Acar, E.","Nilsson, M.","Saunders, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["E."],"propositions":[],"lastnames":["Acar"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Nilsson"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Saunders"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"A flexible modeling framework for coupled matrix and tensor factorizations","year":"2014","pages":"111-115","abstract":"Joint analysis of data from multiple sources has proved useful in many disciplines including metabolomics and social network analysis. However, data fusion remains a challenging task in need of data mining tools that can capture the underlying structures from multi-relational and heterogeneous data sources. In order to address this challenge, data fusion has been formulated as a coupled matrix and tensor factorization (CMTF) problem. Coupled factorization problems have commonly been solved using alternating methods and, recently, unconstrained all-at-once optimization algorithms. In this paper, unlike previous studies, in order to have a flexible modeling framework, we use a general-purpose optimization solver that solves for all factor matrices simultaneously and is capable of handling additional linear/nonlinear constraints with a nonlinear objective function. We formulate CMTF as a constrained optimization problem and develop accurate models more robust to overfactoring. The effectiveness of the proposed modeling/algorithmic framework is demonstrated on simulated and real data.","keywords":"data mining;matrix decomposition;optimisation;sensor fusion;tensors;coupled matrix and tensor factorization problem;flexible modeling framework;data fusion;CMTF problem;general-purpose optimization solver;constrained optimization problem;all factor matrices;nonlinear objective function;unconstrained all-at-once optimization algorithms;Tensile stress;Data models;Optimization;Data integration;Nuclear magnetic resonance;Chemicals;Joints;data fusion;tensor factorizations;nonlinear optimization;nonlinear constraints;SNOPT","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569911163.pdf","bibtex":"@InProceedings{6952001,\n author = {E. Acar and M. Nilsson and M. Saunders},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {A flexible modeling framework for coupled matrix and tensor factorizations},\n year = {2014},\n pages = {111-115},\n abstract = {Joint analysis of data from multiple sources has proved useful in many disciplines including metabolomics and social network analysis. However, data fusion remains a challenging task in need of data mining tools that can capture the underlying structures from multi-relational and heterogeneous data sources. In order to address this challenge, data fusion has been formulated as a coupled matrix and tensor factorization (CMTF) problem. Coupled factorization problems have commonly been solved using alternating methods and, recently, unconstrained all-at-once optimization algorithms. In this paper, unlike previous studies, in order to have a flexible modeling framework, we use a general-purpose optimization solver that solves for all factor matrices simultaneously and is capable of handling additional linear/nonlinear constraints with a nonlinear objective function. We formulate CMTF as a constrained optimization problem and develop accurate models more robust to overfactoring. The effectiveness of the proposed modeling/algorithmic framework is demonstrated on simulated and real data.},\n keywords = {data mining;matrix decomposition;optimisation;sensor fusion;tensors;coupled matrix and tensor factorization problem;flexible modeling framework;data fusion;CMTF problem;general-purpose optimization solver;constrained optimization problem;all factor matrices;nonlinear objective function;unconstrained all-at-once optimization algorithms;Tensile stress;Data models;Optimization;Data integration;Nuclear magnetic resonance;Chemicals;Joints;data fusion;tensor factorizations;nonlinear optimization;nonlinear constraints;SNOPT},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569911163.pdf},\n}\n\n","author_short":["Acar, E.","Nilsson, M.","Saunders, M."],"key":"6952001","id":"6952001","bibbaseid":"acar-nilsson-saunders-aflexiblemodelingframeworkforcoupledmatrixandtensorfactorizations-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569911163.pdf"},"keyword":["data mining;matrix decomposition;optimisation;sensor fusion;tensors;coupled matrix and tensor factorization problem;flexible modeling framework;data fusion;CMTF problem;general-purpose optimization solver;constrained optimization problem;all factor matrices;nonlinear objective function;unconstrained all-at-once optimization algorithms;Tensile stress;Data models;Optimization;Data integration;Nuclear magnetic resonance;Chemicals;Joints;data fusion;tensor factorizations;nonlinear optimization;nonlinear constraints;SNOPT"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.577Z","downloads":0,"keywords":["data mining;matrix decomposition;optimisation;sensor fusion;tensors;coupled matrix and tensor factorization problem;flexible modeling framework;data fusion;cmtf problem;general-purpose optimization solver;constrained optimization problem;all factor matrices;nonlinear objective function;unconstrained all-at-once optimization algorithms;tensile stress;data models;optimization;data integration;nuclear magnetic resonance;chemicals;joints;data fusion;tensor factorizations;nonlinear optimization;nonlinear constraints;snopt"],"search_terms":["flexible","modeling","framework","coupled","matrix","tensor","factorizations","acar","nilsson","saunders"],"title":"A flexible modeling framework for coupled matrix and tensor factorizations","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}