Document clustering based on non-negative matrix factorization

By Wei Xu, Xin Liu, Yihong Gong. 2003

2,153 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-Relational Latent Semantic Analysis (2013, background): “Continuous semantic space representations have proven successful in a wide variety of NLP and IR applications, such as document clustering (Xu et al., 2003) and cross-lingual document retrieval (Dumais et al., 1997; Platt et al., 2010) at the document level and sentential semantics (Guo and Diab,…”
Joint Unsupervised Learning of Deep Representations and Image Clusters (2016, methodology): “We report NMI for different methods on various datasets.”
Discriminative Improvements to Distributional Sentence Similarity (2013, background): “However, recent work has demonstrated the robustness of nonnegative matrix factorization (NMF; Lee and Seung, 2001) for text mining tasks (Xu et al., 2003; Arora et al., 2012); the difference from SVD is the addition of a non-negativity constraint in the latent representation based on…”
On Deep Multi-View Representation Learning (2015, methodology): “The AC and NMI results (in percent) for each algorithm are given in Table 1.”
Laplacian Score for Feature Selection (2005, methodology): “Two metrics, the accuracy (AC) and the normalized mutual information metric (MI) are used to measure the clustering performance [ 6 ].”
Meta-Learning to Cluster (2019, methodology): “Clustering is one of the most ubiquitous techniques in data analysis that has important applications in numerous domains that extend far beyond machine learning [Xu et al., 2003, Cai et al., 2004, Tung et al., 2010, Xu and Tian, 2015].”
Robust (Semi) Nonnegative Graph Embedding (2014, background): “NMF has been shown to be successful in a variety of applications, such as image processing [12]–[14] and text analysis [15].”
Sparse Nonnegative Matrix Factorization for Clustering (2008, background): “In the Principal Component Analysis (PCA), to the contrary, interpretation after lower rank approximation may become difficult when the data matrix is nonnegative since it allows negative elements in the factors.”
A Survey of Text Clustering Algorithms (2012, methodology): “The non-negative matrix factorization (NMF) technique is a latentspace method, and is particularly suitable to clustering [97].”
Outlier Detection for Text Data (2017, methodology): “[25] experimented with NMF for document clustering instead of SVD based Latent Semantic Indexing (LSI).”
Graph Regularized Nonnegative Matrix Factorization for Data Representation (2011, methodology): “It can achieve similar or better performance than most of the state-of-theart clustering algorithms, including the popular spectral clustering methods [32], [42].”
Non-negative Matrix Factorization on Manifold (2008, methodology): “Previous studies show that NMF is very powerful on clustering [29, 24].”
SVD based initialization: A head start for nonnegative matrix factorization (2008, methodology): “Each column of W corresponds to a basic document, and the resulting k documents can be additively combined using coefficients from H to reconstruct an approximation of the document collection as well as for other applications profiting from dimensional reduction such as clustering [8] [15] [16].”
Locally Consistent Concept Factorization for Document Clustering (2011, methodology): “• Nonnegative Matrix Factorization based clustering (NMF in short) [25].”
On the Equivalence of Nonnegative Matrix Factorization and Spectral Clustering (2005, background): “A number of researches on further developing NMF computational methodologies [12, 11, 10], and applications on text mining [9, 14, 11].”
Deep Spectral Clustering Using Dual Autoencoder Network (2019, methodology): “In recent years, many clustering methods have been proposed, such asK-means clustering [24], spectral clustering [27, 42], and non-negative matrix factorization clustering [37], among whichK-means and spectral clustering are two well-known”