Parallel Spectral Clustering in Distributed Systems

By Wen-Yen Chen, Yangqiu Song, Hongjie Bai, Chih-Jen Lin, Edward Y. Chang. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011

652 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f66c25b635539bf35bd001219d35df1b4805aa85

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

In Media Technology

Citations in the corpus

Binary Multi-View Clustering (2019, background): “Unfortunately, SC cannot be directly applied to large-scale datasets either, due to the expensive adjacency matrix and eigenspace constructions [9].”
Leveraging social media networks for classification (2011, background): “Both have been extended to distributed cases [16,6,8].”
A Comprehensive Survey of Clustering Algorithms (2015, background): “The main basic ideas of clustering for big data can be summarized in the following 4 categories: (1) sample clustering [10,18]; (2) data merged clustering [17,134]; (3) dimension-reducing clustering [135,136]; (4) parallel clustering [114,137–139]; Typical algorithms of this kind of clustering areK-”
Large Scale Spectral Clustering with Landmark-Based Representation (2011, methodology): “There are several variants available for Nyström approximation based spectral clustering, and we choose the Matlab implementation with orthogonalization (Chen et al. 2010), which is available online 6 .”
CUDA-Based Parallelization of Power Iteration Clustering for Large Datasets (2017, background): “Sparse implementations of the affinity matrix have shown to be a promising strategy to improve scalability [6].”
Compressive Spectral Clustering (2016, neutral): “3.2 of (Chen et al., 2011)).”
Self-Taught Convolutional Neural Networks for Short Text Clustering (2017, methodology): “Normalized mutual information [51] between tag/label set T and cluster set C is a popular metric used for evaluating clustering tasks.”
Robust Structured Subspace Learning for Data Representation (2015, methodology): “To demonstrate the performance of our method, we take all the original features for clustering as baseline and compare it with a various of representative algorithms, including spectral clustering (SC) [45], PCA [2], LPP [6] and several unsupervised feature selection methods, i.”
Learning Deep Representations for Graph Clustering (2014, methodology): “There are works towards efficient implementation of spectral clustering such as (Chen et al. 2011), in which the authors’ aim is to construct a sparse similarity graph as the input to the parallelized spectral clustering method, whereas what we aim to achieve is to replace the expensive EVD in…”
Parameter Server for Distributed Machine Learning (2013, background): “Of course, beyond these general frameworks, numerous systems have been developed that target specific applications, such as [3, 13, 24, 22, 28, 10, 15].”
Large-Scale Multi-View Spectral Clustering via Bipartite Graph (2015, background): “Many works have been proposed to accelerate SC algorithm (Fowlkes et al. 2004), (Shinnou and Sasaki 2008), (Sakai and Imiya 2009), (Yan, Huang, and Jordan 2009), (Chen et al. 2011), (Chen and Cai 2011).”
A Comparative Study of Efficient Initialization Methods for the K-Means Clustering Algorithm (2012, methodology): “For this reason, it can be used to initialize more expensive clustering algorithms such as expectation maximization [8], DBSCAN [9], and spectral clustering [10].”
Comprehensive survey on hierarchical clustering algorithms and the recent developments (2022, methodology): “…c l u s t e r i ng m e t hod s (Zahn 1971; Guan and Du 1998), CLICK (Sharan and Shamir 2000), Spectral clustering (von Luxburg 2007), improvements of Spectral clustering (Chen et al. 2011; Cai and Chen 2015; He et al. 2019; Huang et al. 2020), and Kemighan–Lin (KL) method (Kernighan and Lin 1970).”
Social big data: Recent achievements and new challenges (2015, positive): “Some new developments related to traditional clustering algorithms, such as the K-mean [137] , EM [138] , which has been modified to work with the MapReduce paradigm, and more sophisticated approaches based on graph computing (such as spectral clustering), are currently being developed [139] [140] [”
Ultra-Scalable Spectral Clustering and Ensemble Clustering (2019, methodology): “The Nystr€ om method [3] randomly selects p representatives from the original dataset and builds an N p affinity sub-matrix.”
Large Scale Spectral Clustering Via Landmark-Based Sparse Representation (2015, methodology): “3) Nyström: There are several variants available for Nyström approximation-based spectral clustering, and we choose the MATLAB implementation with orthogonalization [5], which is available online.”