Filters








4 Hits in 2.3 sec

MPI-FAUN: An MPI-Based Framework for Alternating-Updating Nonnegative Matrix Factorization [article]

Ramakrishnan Kannan, Grey Ballard, Haesun Park
2016 arXiv   pre-print
Non-negative matrix factorization (NMF) is the problem of determining two non-negative low rank factors W and H, for the given input matrix A, such that A ≈ W H.  ...  The framework is flexible and able to leverage a variety of NMF and NLS algorithms, including Multiplicative Update, Hierarchical Alternating Least Squares, and Block Principal Pivoting.  ...  Also, partial funding for this work was provided by AFOSR Grant FA9550-13-1-0100, National Science Foundation (NSF) grants IIS-1348152 and ACI-1338745, Defense Advanced Research Projects Agency (DARPA)  ... 
arXiv:1609.09154v1 fatcat:xtcsszubtbeafnffj4ogr7wppq

Partitioning and Communication Strategies for Sparse Non-negative Matrix Factorization

Oguz Kaya, Ramakrishnan Kannan, Grey Ballard
2018 Proceedings of the 47th International Conference on Parallel Processing - ICPP 2018  
Non-negative matrix factorization (NMF), the problem of finding two non-negative low-rank factors whose product approximates an input matrix, is a useful tool for many data mining and scientific applications  ...  Key-words: sparse non-negative matrix factorization, hypergraph partitioning, parallel algorithms * For the published version of this research report, please refer to https://doi.  ...  Kannan, Ballard and Park [11, 12] , have proposed Mpi-Faun framework to implement various NMF algorithms such as multiplicative update (MU), Hierarchical Alternating Least Squares (HALS) and Alternating  ... 
doi:10.1145/3225058.3225127 dblp:conf/icpp/KayaKB18 fatcat:bbi6k72rmbfyfc27peh3osa7hy

Fast and Secure Distributed Nonnegative Matrix Factorization

Yuqiu Qian, Conghui Tan, Danhao Ding, Hui Li, Nikos Mamoulis
2020 IEEE Transactions on Knowledge and Data Engineering  
Firstly, we propose a distributed sketched alternating nonnegative least squares (DSANLS) framework for NMF, which utilizes a matrix sketching technique to reduce the size of nonnegative least squares  ...  Nonnegative matrix factorization (NMF) has been successfully applied in several data mining tasks.  ...  The state-of-the-art distributed NMF is MPI-FAUN [8] , a general framework that iteratively solves the nonnegative least squares (NLS) subproblems for U and V .  ... 
doi:10.1109/tkde.2020.2985964 fatcat:e6fq2obogjg5zhbatmmcz6rezm

2018 Index IEEE Transactions on Knowledge and Data Engineering Vol. 30

2019 IEEE Transactions on Knowledge and Data Engineering  
., þ, TKDE March 2018 517-529 MPI-FAUN: An MPI-Based Framework for Alternating-Updating Nonnegative Matrix Factorization.  ...  ., þ, TKDE Feb. 2018 305-324 MPI-FAUN: An MPI-Based Framework for Alternating-Updating Nonnegative Matrix Factorization.  ... 
doi:10.1109/tkde.2018.2882359 fatcat:asiids266jagrkx5eac6higrlq