On the equivalence between Non-negative Matrix Factorization and Probabilistic Latent Semantic Indexing

By Chris H. Q. Ding, Tao Li, Wei Peng. Computational Statistics & Data Analysis, 2008

311 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e7a041dca59381c99ffaaa28ab1143b7877bd42f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tao Li
2. Greg Ver Steeg
3. Nicolas Gillis
4. Brian Karrer
5. Mark Newman
6. Brian Ball
7. Fei Wang
8. Jing Gao

In Computer Vision and Pattern Recognition

1. Nicolas Gillis
2. Tao Li
3. Mark Newman
4. Chris H. Q. Ding
5. Fei Wang
6. Jiawei Han
7. Shenghuo Zhu
8. Xin Wang

Citations in the corpus

• Neural Networks and Deep Learning (2018, unknown): “Probabilistic latent semantic analysis: Refer to [99, 206] for a definition of probabilistic latent semantic analysis.”
• Exploring Topic Coherence over Many Models and Many Topics (2012, background): “Topic labels were chosen in an ad hoc manner only to briefly summarize the topic’s focus. have found a connection between NMF and Proba-bilistic Latent Semantic Analysis (Ding et al., 2008), an extension to LSA.”
• An efficient and principled method for detecting communities in networks (2011, methodology): “The second, from Ding et al. [36], is to alternate between the EM algo-rithm and a nonnegative matrix factorization algorithm, exploiting the fact that both maximize the same objec-tive function but in different ways.”
• Multi-View Clustering via Joint Nonnegative Matrix Factorization (2013, background): “Therefore there could be many possible solutions, and it is important to enforce additional constraints to ensure the uniqueness of the factorization in clustering.”
• The Why and How of Nonnegative Matrix Factorization (2014, background): “Note that NMF is closely related to existing topic models, in particular probabilistic latent semantic analysis and indexing (PLSA and PLSI) [45, 37].”
• Community discovery using nonnegative matrix factorization (2011, background): “Moreover, they also show that the results of NMF could be more easily explained ( Ding et al. 2008 ).”
• Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledge (2016, background): “These mechanisms may be explicitly stated, as in Latent Dirichlet Allocation (LDA) (Blei et al., 2003), or implicitly stated, as with matrix factorization techniques (Hofmann, 1999; Ding et al., 2008; Buntine and Jakulin, 2006).”