Adaptive computation of the symmetric nonnegative matrix factorization (SymNMF)

DOI10.1007/S40324-019-00211-ZMaRDI QIDQ777470zbMATH OpenOpenAlexWikidataFDO

Authors Paola Favati, Grazia Lotti, Francesco Romani, Ornella Menchi

Publication date 7 July 2020

Published in S\(\vec{\text{e}}\)MA Journal (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1903.01321

zbMATH Keywords

graph clusteringsymmetric nonnegative matrix factorization

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Complexity and performance of numerical algorithms (65Y20) Analysis of algorithms and problem complexity (68Q25) Numerical methods for low-rank matrix approximation; matrix compression (65F55)

Abstract: Nonnegative Matrix Factorization (NMF), first proposed in 1994 for data analysis, has received successively much attention in a great variety of contexts such as data mining, text clustering, computer vision, bioinformatics, etc. In this paper the case of a symmetric matrix is considered and the symmetric nonnegative matrix factorization (SymNMF) is obtained by using a penalized nonsymmetric minimization problem. Instead of letting the penalizing parameter increase according to an a priori fixed rule, as suggested in literature, we propose a heuristic approach based on an adaptive technique. Extensive experimentation shows that the proposed algorithm is effective.

Recommendations

• SymNMF: nonnegative low-rank approximation of a similarity matrix for graph clustering
• Off-diagonal symmetric nonnegative matrix factorization
• A symmetric rank-one quasi-Newton method for nonnegative matrix factorization
• scientific article; zbMATH DE number 7404610
• Four algorithms to solve symmetric multi-type non-negative matrix tri-factorization problem

Cites work

• scientific article; zbMATH DE number 852536 (Why is no real title available?)
• scientific article; zbMATH DE number 883145 (Why is no real title available?)
• Algorithms for nonnegative matrix and tensor factorizations: a unified view based on block coordinate descent framework
• Fast nonnegative matrix factorization: an active-set-like method and comparisons
• Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method
• Nonnegative matrix factorization for spectral data analysis
• On the convergence of the block nonlinear Gauss-Seidel method under convex constraints
• Projected Gradient Methods for Nonnegative Matrix Factorization
• SymNMF: nonnegative low-rank approximation of a similarity matrix for graph clustering

Cited in

(5)

• scientific article; zbMATH DE number 7295421 (Why is no real title available?)
• Four algorithms to solve symmetric multi-type non-negative matrix tri-factorization problem
• Efficient method for symmetric nonnegative matrix factorization with an approximate augmented Lagrangian scheme
• Off-diagonal symmetric nonnegative matrix factorization
• A symmetric rank-one quasi-Newton method for nonnegative matrix factorization

Describes a project that uses

Uses Software

• SymNMF

This page was built for publication: Adaptive computation of the symmetric nonnegative matrix factorization (SymNMF)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q777470)