Abstract
This paper presents two methods for nonnegative matrix factorization based on an inertial projection neural network (IPNN). The first method applies two IPNNs for optimizing one matrix, with the other fixed alternatively, while the second optimizes two matrices simultaneously using a single IPNN. With the proposed methods, different local optimum solutions can be found under the same initial conditions, whereas most traditional methods can only find one local optimum solution. Moreover, experimental results on synthetic data, signal processing, and clustering in real-world data demonstrate the effectiveness and performance of the proposed methods.
Similar content being viewed by others
References
Zhou G, Andrzej C, Xie S (2012) Fast nonnegative matrix/tensor factorization based on low-rank approximation. IEEE Trans Signal Process 60(6):2928–2940
Liu H, Yang Z, Yang J, Wu Z, Li X (2014) Local coordinate concept factorization for image representation. IEEE Trans Neural Netw Learn Syst 25(6):1071–1082
Zoidi O, Tefas A, Pitas T (2013) Multiplicative update rules for concurrent nonnegative matrix factorization and maximum margin classification. IEEE Trans Neural Netw Learn Syst 24(3):422–434
Sidiropoulos ND, Huang K, Swami A (2014) Non-negative matrix factorization revisited: uniqueness and algorithm for symmetric decomposition. IEEE Trans Signal Process 62(1):211–224
Ren W, Li G, Tu D, Jia L (2014) Nonnegative matrix factorization with regularizations. IEEE J Emerg Sel Top Circuits Syst 4(1):153–164
Chorowski J, Zurada JM (2015) Learning understandable neural networks with nonnegative weight constraints. IEEE Trans Neural Netw Learn Syst 26(1):62–69
Cai D, He XF, Han JW et al (2011) Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Pattern Anal Mach Intell 33(8):1548–1560
Li P, Bu J, Zhang L, Chen C (2015) Graph-based local concept coordinate factorization. Knowl Inf Syst 43(1):103–126
Li P, Bu J, Ji R, Chun C, Cai D (2014) Discriminative orthogonal nonnegative matrix factorization with flexibility for data representation. Expert Syst Appl 41(2):1283–1293
Li P, Bu J, chen C, He Z, Cai D (2013) Relational multimanifold coclustering. IEEE Trans Cybern 43(6):1871
Li P, Bu J, chen C, Wang C, Cai D (2013) Subspace learning via locally constrained a-optimal nonnegative projection. Neurocomputing 115:49–62
Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Nature 401(6755):788–791
Paatero P, Tapper U (1994) Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values. Environmetrics 5(2):111–126
Lee DD, Seung HS (2001) Algorithms for non-negative matrix factorization. In: Advances in neural information processing systems, pp 556–562
Berry MW, Browne M, Langville AN, Pauca Amy N VP, Plemmons RJ (2007) Algorithms and applications for approximate nonnegative matrix factorization. Comput Stat Data Anal 52(1):155–173
Lin CJ (2007) Projected gradient methods for nonnegative matrix factorization. Neural Comput 19(10):2756–2779
Zdunek R, Cichocki A (2006) Non-negative matrix factorization with quasi-Newton optimization. In: International conference on artificial intelligence and soft computing, pp 870–879. Springer
Pierre C (2007) Fast newton-type methods for the least squares nonnegative matrix approximation problem. SIAM Int Conf Data Min 1(1):38–51
Han L, Neumann M, Prasad U (2009) Alternating projected barzilai-borwein methods for nonnegative matrix factorization. Electron Trans Numer Anal 36:54–82
Guan N, Tao D, Luo Z, Yuan B (2012) Nenmf: an optimal gradient method for nonnegative matrix factorization. IEEE Trans Signal Process 60(6):2882–2898
Hopfield JJ, Tank DW (1985) neural computation of decisions in optimization problems. Biol Cybern 52(3):141–152
Xia Y, Leung H, Wang J (2002) A projection neural network and its application to constrained optimization problems. IEEE Trans Circuits Syst I Fundam Theory Appl 49(4):447–458
He X, Huang T, Yu J et al (2017) An inertial projection neural network for solving variational inequalities. IEEE Trans Cybern 47(3):809–814
Che H, He X, Li C, Huang T (2015) An intelligent method of swarm neural networks for equalities-constrained nonconvex optimization. Neurocomputing 167:569–577
Wang J (1993) Analysis and design of a recurrent neural network for linear programming. IEEE Trans Circuits Syst I Fundam Theory Appl 40(9):613–618
Hu X, Zhang B (2009) An alternative recurrent neural network for solving variational inequalities and related optimization problems. IEEE Trans Syst Man Cybern B (Cybern) 39(6):1640–1645
Li C, Yu X, Huang T et al (2016) A generalized Hopfield network for nonsmooth constrained convex optimization: Lie derivative approach. IEEE Trans Neural Netw Learn Syst 27(2):308–321
Hu X, Wang J (2007) Design of general projection neural networks for solving monotone linear variational inequalities and linear and quadratic optimization problems. IEEE Trans Syst Man Cybern B (Cybern) 37(5):1414–1421
Yan Z, Wang J, Li G (2014) A collective neurodynamic optimization approach to bound-constrained nonconvex optimization. Neural Netw 55:20–29
Liu Q, Wang J (2008) A one-layer recurrent neural network with a discontinuous hard-limiting activation function for quadratic programming. IEEE Trans Neural Netw 19(4):558–570
Fan J, Wang J (2016) A collective neurodynamic optimization approach to nonnegative matrix factorization. IEEE Trans Neural Netw 99:1–13
Yan Z, Wang J (2015) Nonlinear model predictive control based on collective neurodynamic optimization. IEEE Trans Neural Netw Learn Syst 26(4):840–850
Shi J, Ren X, Dai G, Wang J, Zhang Z (2011) A non-convex relaxation approach to sparse dictionary learning. In: 2011 IEEE conference on computer vision and pattern recognition (CVPR), pp 1809–1816. IEEE
Li G, Yan Z, Wang J (2015) A one-layer recurrent neural network for constrained nonconvex optimization. Neural Netw 61:10–21
Chen G, Li C, Dong Z (2017) Parallel and distributed computation for dynamical economic dispatch. IEEE Trans Smart Grid 99:1–1
Li H, Chen G, Huang T, Dong Z (2016) High-performance consensus control in networked systems with limited bandwidth communication and time-varying directed topologies. IEEE Trans Neural Netw Learn Syst 28(5):1043–1054
Li H, Chen G, Huang T et al (2016) Event-triggered distributed average consensus over directed digital networks with limited communication bandwidth. IEEE Trans Cybern 46(12):3098–3110
He X, Li C, Huang T et al (2014) A recurrent neural network for solving bilevel linear programming problem. IEEE Trans Neural Netw Learn Syst 25(4):824–830
He X, Liand C, Huang T, Li C, Huang J (2014) A recurrent neural network for solving bilevel linear programming problem. IEEE Trans Neural Netw Learn Syst 25(4):824
He X, Ho DWC, Huang T et al (2017) Second-order continuous-time algorithms for economic power dispatch in smart grids. IEEE Trans Syst Man Cybern: Syst. https://doi.org/10.1109/TSMC.2017.26722051
Li H, Chen G, Liao X, Huang T (2016) Leader-following consensus of discrete-time multiagent systems with encodingcdecoding. IEEE Trans Circuits Syst II Express Briefs 63(4):401–405
Bertsekas DP (1999) Nonlinear programming. Athena Scientific, Belmont
Acknowledgements
This work is supported by Natural Science Foundation of China (Grant No.: 61374078).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest.
Rights and permissions
About this article
Cite this article
Dai, X., Li, C., He, X. et al. Nonnegative matrix factorization algorithms based on the inertial projection neural network. Neural Comput & Applic 31, 4215–4229 (2019). https://doi.org/10.1007/s00521-017-3337-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-017-3337-5