TY - GEN
T1 - Distributed HALS Algorithm for NMF based on Simple Average Consensus Algorithm
AU - Hayashi, Keiju
AU - Migita, Tsuyoshi
AU - Takahashi, Norikazu
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number JP21H03510.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Nonnegative Matrix Factorization (NMF) is an efficient dimensionality reduction method for nonnegative data. Recently, a distributed algorithm has been proposed for multiple agents in a network to execute the hierarchical alternating least squares algorithm, which is well known as a fast computation method for NMF. However, the average consensus algorithm used there requires each agent to store the entire history of the values of its variables until the complete average consensus is reached, which increases the memory usage and computational cost. In this paper, we propose to replace the complicated average consensus algorithm with a simple one, and show through simulations that this replacement does not degrade the quality of the result if the values of the hyper-parameters are properly chosen.
AB - Nonnegative Matrix Factorization (NMF) is an efficient dimensionality reduction method for nonnegative data. Recently, a distributed algorithm has been proposed for multiple agents in a network to execute the hierarchical alternating least squares algorithm, which is well known as a fast computation method for NMF. However, the average consensus algorithm used there requires each agent to store the entire history of the values of its variables until the complete average consensus is reached, which increases the memory usage and computational cost. In this paper, we propose to replace the complicated average consensus algorithm with a simple one, and show through simulations that this replacement does not degrade the quality of the result if the values of the hyper-parameters are properly chosen.
KW - average consensus
KW - distributed algorithm
KW - hierarchical alternating least squares algorithm
KW - multiagent system
KW - nonnegative matrix factorization
UR - http://www.scopus.com/inward/record.url?scp=85125805278&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125805278&partnerID=8YFLogxK
U2 - 10.1109/PIC53636.2021.9687076
DO - 10.1109/PIC53636.2021.9687076
M3 - Conference contribution
AN - SCOPUS:85125805278
T3 - Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021
SP - 41
EP - 47
BT - Proceedings of the 2021 IEEE International Conference on Progress in Informatics and Computing, PIC 2021
A2 - Wang, Yinglin
A2 - Zhang, Zheying
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th IEEE International Conference on Progress in Informatics and Computing, PIC 2021
Y2 - 17 December 2021 through 19 December 2021
ER -