DocumentCode :
2147954
Title :
Parallel Simultaneous Co-clustering and Learning with Map-Reduce
Author :
Deodhar, Meghana ; Jones, Clinton ; Ghosh, Joydeep
Author_Institution :
Electr. & Comput. Eng., Univ. of Texas at Austin, Austin, TX, USA
fYear :
2010
fDate :
14-16 Aug. 2010
Firstpage :
149
Lastpage :
154
Abstract :
Many data mining applications involve predictive modeling of very large, complex datasets. Such applications present a need for innovative algorithms and associated implementations that are not only effective in terms of prediction accuracy, but can also be efficiently run on distributed computational systems to yield results in reasonable time. This paper focuses on predictive modeling of multirelational data such as dyadic data with associated covariates or “side-information”. We first give illustrative examples of applications that involve such data and then describe a general framework based on Simultaneous CO-clustering And Learning (SCOAL), which applies a divide-and-conquer approach to data analysis. We show that the main elements of the SCOAL algorithm can be effectively parallelized using the Map-Reduce framework. Experiments on Amazon´s EC2 demonstrate that the proposed parallelizations result in considerable improvements in run time when using a cluster of machines.
Keywords :
data analysis; data mining; divide and conquer methods; parallel processing; pattern clustering; Map-Reduce framework; SCOAL algorithm; data analysis; data mining; distributed computational systems; divide-and-conquer approach; dyadic data; multirelational data; parallel simultaneous coclustering; parallel simultaneous learning; predictive modeling; very large complex datasets; Clustering algorithms; Computational modeling; Data mining; Data models; Motion pictures; Prediction algorithms; Predictive models; Map-Reduce; distributed data mining; dyadic data; predictive modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Granular Computing (GrC), 2010 IEEE International Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-7964-1
Type :
conf
DOI :
10.1109/GrC.2010.54
Filename :
5576169
Link To Document :
بازگشت