Community discovery using nonnegative matrix factorization
By Fei Wang, Tao Li, Xin Wang, Shenghuo Zhu, Chris H. Q. Ding. Data mining and knowledge discovery, 2011
436 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/df89be8356e1f2c6bd2269ef6fb1bc326c149e50
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 Statistical and Nonlinear Physics
Citations in the corpus
- Cross View Link Prediction by Learning Noise-resilient Representation Consensus (2017, methodology): “Some work investigates the low rank approximation methods by generating a low rank matrix to approximate the adjacency matrix of network structure [24] [15].”
- InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (2019, background): “There has been a significant amount of previous work done studying many aspects of graphs including link prediction [13, 57] and node prediction [2].”
- Community Preserving Network Embedding (2017, background): “By lemma 4 in (Wang et al. 2011), we have and By lemma 6 in (Wang et al. 2011), we have (20) By lemma 2 in (Wang et al. 2011), we have (21) By lemmas 6 and 7 in (Wang et al. 2011), we have where By combining (18), (19), (20), (21) and (22), we have the final auxiliary function in lemma 2.”
- Improve collaborative filtering through bordered block diagonal form matrices (2013, neutral): “Some previous research has been performed attempting to address these problems, which mainly focus on various matrix-clustering [11, 26, 27, 39, 34] or community detection [6, 36, 23] techniques.”
- An efficient and principled method for detecting communities in networks (2011, methodology): “Several papers have recently proposed using NMF to find overlapping communities [22, 28, 29], and the work of Psorakis et al. [22] in particular uses NMF with the PLSA model, although again in an asymmetric formulation, and not applied to link communities.”
- The Why and How of Nonnegative Matrix Factorization (2014, background): “Other applications include air emission control [97], computational biology [34], blind source separation [22], single-channel source separation [82], clustering [35], music analysis [42], collaborative filtering [92], and community detection [106].”
- A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning (2021, methodology): “These include heuristic optimization (multi-objective) [19], [20], matrix factorization [21], [22] and Bayesian model [23].”