Abstract
| Original language | English |
|---|---|
| Title of host publication | Latent Variable Analysis and Signal Separation : 14th International Conference, LVA/ICA 2018, Guildford, UK, July 2–5, 2018, Proceedings |
| Editors | Yannick Deville , Sharon Gannot , Russell Mason , Mark D. Plumbley , Dominic Ward |
| Number of pages | 11 |
| Publication date | 2018 |
| Pages | 488-498 |
| ISBN (Print) | 978-3-319-93763-2 |
| ISBN (Electronic) | 978-3-319-93764-9 |
| DOIs | |
| Publication status | Published - 2018 |
| Event | 14th International Conference on Latent Variable Analysis and Signal Separation - University of Surrey, Guildford, United Kingdom Duration: 2 Jul 2018 → 5 Jul 2018 Conference number: 14 |
Conference
| Conference | 14th International Conference on Latent Variable Analysis and Signal Separation |
|---|---|
| Number | 14 |
| Location | University of Surrey |
| Country | United Kingdom |
| City | Guildford |
| Period | 02/07/2018 → 05/07/2018 |
| Series | Lecture Notes in Computer Science |
|---|---|
| Volume | 10891 |
| ISSN | 0302-9743 |
Keywords
- Bayesian modeling
- Non-negative matrix factorization
- Sparse non-negative matrix factorization
- Sparsity
Cite this
}
Probabilistic sparse non-negative matrix factorization. / Hinrich, Jesper Løve; Mørup, Morten.
Latent Variable Analysis and Signal Separation: 14th International Conference, LVA/ICA 2018, Guildford, UK, July 2–5, 2018, Proceedings. ed. / Yannick Deville; Sharon Gannot; Russell Mason; Mark D. Plumbley; Dominic Ward. 2018. p. 488-498 (Lecture Notes in Computer Science, Vol. 10891).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
TY - GEN
T1 - Probabilistic sparse non-negative matrix factorization
AU - Hinrich, Jesper Løve
AU - Mørup, Morten
PY - 2018
Y1 - 2018
N2 - In this paper, we propose a probabilistic sparse non-negative matrix factorization model that extends a recently proposed variational Bayesian non-negative matrix factorization model to explicitly account for sparsity. We assess the influence of imposing sparsity within a probabilistic framework on either the loading matrix, score matrix, or both and further contrast the influence of imposing an exponential or truncated normal distribution as prior. The probabilistic methods are compared to conventional maximum likelihood based NMF and sparse NMF on three image datasets; (1) A (synthetic) swimmer dataset, (2) The CBCL face dataset, and (3) The MNIST handwritten digits dataset. We find that the probabilistic sparse NMF is able to automatically learn the level of sparsity and find that the existing probabilistic NMF as well as the proposed probabilistic sparse NMF prunes inactive components and thereby automatically learns a suitable number of components. We further find that accounting for sparsity can provide more part based representations but for the probabilistic modeling the choice of priors and how sparsity is imposed can have a strong influence on the extracted representations.
AB - In this paper, we propose a probabilistic sparse non-negative matrix factorization model that extends a recently proposed variational Bayesian non-negative matrix factorization model to explicitly account for sparsity. We assess the influence of imposing sparsity within a probabilistic framework on either the loading matrix, score matrix, or both and further contrast the influence of imposing an exponential or truncated normal distribution as prior. The probabilistic methods are compared to conventional maximum likelihood based NMF and sparse NMF on three image datasets; (1) A (synthetic) swimmer dataset, (2) The CBCL face dataset, and (3) The MNIST handwritten digits dataset. We find that the probabilistic sparse NMF is able to automatically learn the level of sparsity and find that the existing probabilistic NMF as well as the proposed probabilistic sparse NMF prunes inactive components and thereby automatically learns a suitable number of components. We further find that accounting for sparsity can provide more part based representations but for the probabilistic modeling the choice of priors and how sparsity is imposed can have a strong influence on the extracted representations.
KW - Bayesian modeling
KW - Non-negative matrix factorization
KW - Sparse non-negative matrix factorization
KW - Sparsity
U2 - 10.1007/978-3-319-93764-9_45
DO - 10.1007/978-3-319-93764-9_45
M3 - Article in proceedings
SN - 978-3-319-93763-2
T3 - Lecture Notes in Computer Science
SP - 488
EP - 498
BT - Latent Variable Analysis and Signal Separation
A2 - , Yannick Deville
A2 - , Sharon Gannot
A2 - , Russell Mason
A2 - , Mark D. Plumbley
A2 - , Dominic Ward
ER -