1,369 Hits in 5.1 sec

Overlapping community detection via bounded nonnegative matrix tri-factorization

Yu Zhang, Dit-Yan Yeung
2012 Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '12  
In this paper, based on the matrix factorization approach, we propose a method called bounded nonnegative matrix tri-factorization (BNMTF).  ...  More recently, the focus in this research topic has been switched to the detection of overlapping communities.  ...  In other words, we approximate G by a nonnegative matrix tri-factorization UBU T with bounded U: G ≈Ĝ ≡ UBU T .  ... 
doi:10.1145/2339530.2339629 dblp:conf/kdd/ZhangY12 fatcat:doeaebygrbbstfwt6t6fwnnyy4

Incorporating Implicit Link Preference Into Overlapping Community Detection

Hongyi Zhang, Irwin King, Michael Lyu
Recently, overlapping community detection becomes a trend due to the ubiquity of overlapping and nested communities in real world.  ...  In this paper, we propose a preference-based nonnegative matrix factorization (PNMF) model to incorporate implicit link preference information.  ...  BNMTF (Bounded NM Tri-Factorization) (Zhang and Yeung 2012).  ... 
doi:10.1609/aaai.v29i1.9155 fatcat:6huo2kwb4vbbrfjba3gmgunt4e

Overlapping Communities and the Prediction of Missing Links in Multiplex Networks [article]

Amir Mahdi Abdolhosseini-Qomi, Naser Yazdani, Masoud Asadpour
2020 arXiv   pre-print
We discuss that co-membership in the communities of the similar layers augments the chance of connectivity. The layers are considered similar if they show significant inter-layer community overlap.  ...  ML-BNMTF outperforms baseline methods specifically when the global link overlap is low.  ...  Based on these observations, we continue with proposing a new factorization model called Multi-Layer Bounded Nonnegative Matrix Tri-Factorization (ML-BNMTF), which benefits from the correlated placement  ... 
arXiv:1912.03496v2 fatcat:kz432g7e4nc4baeecjighbnzse

Community Detection in Attributed Graphs: An Embedding Approach

Ye Li, Chaofeng Sha, Xin Huang, Yanchun Zhang
Based on node attributes and community structure embedding, we formulate the attributed community detection as a nonnegative matrix factorization optimization problem.  ...  Extensive experiments conducted on 19 attributed graph datasets with overlapping and non-overlapping ground-truth communities show that our proposed model CDE can accurately identify attributed communities  ...  We note that the communities studied in this paper are allowed to overlap, i.e., g i ∩ g j = ∅ may exist. Nonnegative Matrix Factorization.  ... 
doi:10.1609/aaai.v32i1.11274 fatcat:etyjlyrmr5hbtddozih2xpm26e

A Comprehensive Survey on Community Detection with Deep Learning [article]

Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu
2021 arXiv   pre-print
This survey devises and proposes a new taxonomy covering different state-of-the-art methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep  ...  A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis.  ...  DEEP NONNEGATIVE MATRIX FACTORIZATION-BASED COMMUNITY DETECTION In the network embedding domain, Nonnegative Matrix Factorization (NMF) [129] is a particular technique factorizing an adjacency matrix  ... 
arXiv:2105.12584v2 fatcat:matipshxnzcdloygrcrwx2sxr4

Community discovery using nonnegative matrix factorization

Fei Wang, Tao Li, Xin Wang, Shenghuo Zhu, Chris Ding
2010 Data mining and knowledge discovery  
We choose Nonnegative Matrix Factorization (NMF) as our tool to find the communities because of its powerful interpretability and close relationship between clustering methods.  ...  In this paper, we will investigate another important issue, community discovery, in network analysis.  ...  In the following we will introduce an Asymmetric Nonnegative Matrix Factorization (ANMF) approach to detect communities in a directed network.  ... 
doi:10.1007/s10618-010-0181-y fatcat:o3i3ekwrkjgdxi4hrsduirs3cy

Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection [article]

Artem Lutov, Dingqi Yang, Philippe Cudré-Mauroux
2019 arXiv   pre-print
graph via computationally expensive matrix factorization techniques.  ...  Current graph embedding approaches either sample a large number of node pairs from a graph to learn node embeddings via stochastic optimization or factorize a high-order proximity/adjacency matrix of the  ...  Conventional spectral clustering is equivalent to nonnegative matrix factorization (NMF) [26] .  ... 
arXiv:1912.08808v1 fatcat:e5yhpvy2hfej7kxndykmit5xte

Modularity functions maximization with nonnegative relaxation facilitates community detection in networks

Jonathan Q. Jiang, Lisa J. McQuay
2012 Physica A: Statistical Mechanics and its Applications  
With the explicit nonnegative constraint, our solutions are very close to the ideal community indicator matrix and can directly assign nodes into communities.  ...  Therefore, the proposed method can be exploited to identify the fuzzy or overlapping communities and thus facilitates the understanding of the intrinsic structure of networks.  ...  This description is just an intuitive concept rather than a rigorous definition, and thus is far way from meeting the requirement for detecting communities in graphs via computational algorithms.  ... 
doi:10.1016/j.physa.2011.08.043 fatcat:jpkgajfcrrduni7zl3jpkif4uq

From $K$-Means to Higher-Way Co-Clustering: Multilinear Decomposition With Sparse Latent Factors

Evangelos E. Papalexakis, Nicholas D. Sidiropoulos, Rasmus Bro
2013 IEEE Transactions on Signal Processing  
For three-and higher-way data, uniqueness of the multilinear decomposition implies that, unlike matrix co-clustering, it is possible to unravel a large number of possibly overlapping co-clusters.  ...  This paper starts from -means and shows how co-clustering can be formulated as a constrained multilinear decomposition with sparse latent factors.  ...  proper spatial resolution of the co-clusters, especially overlapping ones. • Latent sparsity is essential for recovering the correct support information in case of overlapping co-clusters; nonnegativity  ... 
doi:10.1109/tsp.2012.2225052 fatcat:hyjebqtxwrgf5jercwyjzj5fba

Protein Complex Detection via Weighted Ensemble Clustering Based on Bayesian Nonnegative Matrix Factorization

Le Ou-Yang, Dao-Qing Dai, Xiao-Fei Zhang, Vladimir N. Uversky
2013 PLoS ONE  
In this paper, a novel Bayesian Nonnegative Matrix Factorization(NMF)-based weighted Ensemble Clustering algorithm (EC-BNMF) is proposed to detect protein complexes from PPI networks.  ...  Finally, we identify overlapping protein complexes from this network by employing Bayesian NMF model.  ...  As a matrix decomposition techniques, NMF produces a low-dimensional approximation of a nonnegative matrix, in the form of nonnegative factors, which can be formulated as O~XY .  ... 
doi:10.1371/journal.pone.0062158 pmid:23658709 pmcid:PMC3642239 fatcat:znjmap3ljbbxzclcdij6ftic3i

Direction Matters: On Influence-Preserving Graph Summarization and Max-Cut Principle for Directed Graphs

Wenkai Xu, Gang Niu, Aapo Hyvärinen, Masashi Sugiyama
2021 Neural Computation  
Conventional clustering approaches, based on Min-Cut-style criteria, compress both the vertices and edges of the graph into the communities, which lead to a loss of directed edge information.  ...  In this letter, we present a model, based on minimizing reconstruction error with nonnegative constraints, which relates to a Max-Cut criterion that simultaneously identifies the compressed nodes and the  ...  Nonnegative Matrix Factorization (NMF).  ... 
doi:10.1162/neco_a_01402 fatcat:xgztzd7sbzcmhnr2bczlqbb7zu

TRIBAC: Discovering Interpretable Clusters and Latent Structures in Graphs

Jeffrey Chan, Christopher Leckie, James Bailey, Kotagiri Ramamohanarao
2014 2014 IEEE International Conference on Data Mining  
One type of approach for graph clustering is nonnegative matrix factorisation However, the formulations of existing factorisation approaches can be overly relaxed and their groupings and results consequently  ...  To address these challenges, we introduce a new nonnegative matrix tri-factorisation formulation for graph clustering.  ...  Community detection decomposes a graph into a community structure, where vertices from the same communities have many edges between themselves, and vertices of different communities have few edges.  ... 
doi:10.1109/icdm.2014.118 dblp:conf/icdm/ChanLBR14 fatcat:a7lloedrirdg7cjqs5yu3vqszu

Transductive Nonnegative Matrix Tri-Factorization

Xiao Teng, Long Lan, Xiang Zhang, Guohua Dong, Zhigang Luo
2020 IEEE Access  
INDEX TERMS Nonnegative matrix factorization, nonnegative matrix tri-factorization, transductive learning.  ...  Different from standard NMF, nonnegative matrix tri-factorization (NMTF) decomposes a nonnegative matrix into the product of three lower-rank nonnegative matrices, and thus provides a flexible framework  ...  Nonnegative matrix tri-factorization (NMTF), which seeks a 3-factor decomposition, has become an emerging tool for co-clustering.  ... 
doi:10.1109/access.2020.2989527 fatcat:ux7lny42gjag5ftaa2tvmf42ay

Identifying Protein Complexes With Clear Module Structure Using Pairwise Constraints in Protein Interaction Networks

Guangming Liu, Bo Liu, Aimin Li, Xiaofan Wang, Jian Yu, Xuezhong Zhou
2021 Frontiers in Genetics  
To tackle these challenges, we propose a novel semi-supervised protein complex detection model based on non-negative matrix tri-factorization, which not only considers topological structure of a PPI network  ...  We propose non-overlapping (NSSNMTF) and overlapping (OSSNMTF) protein complex detection algorithms to identify the significant protein complexes with clear module structures from PPI networks.  ...  To overcome the drawback of NMF and SNMF, a bounded nonnegative matrix tri-factorization (Jing et al., 2012) , NMTF, has been proposed which is formulated as J 3 (F, G) = min F≥0,G≥0 A − FGF T 2 F (3)  ... 
doi:10.3389/fgene.2021.664786 pmid:34512712 pmcid:PMC8430217 fatcat:lw3divhb3rafbkxbzzmppvh42u

Overlapping community detection in networks

Jierui Xie, Stephen Kelley, Boleslaw K. Szymanski
2013 ACM Computing Surveys  
This paper reviews the state of the art in overlapping community detection algorithms, quality measures, and benchmarks.  ...  In addition to community level evaluation, we propose a framework for evaluating algorithms' ability to detect overlapping nodes, which helps to assess over-detection and under-detection.  ...  Non-negative Matrix Factorization (NMF) is a feature extraction and dimensionality reduction technique in machine learning that has been adapted to community detection.  ... 
doi:10.1145/2501654.2501657 fatcat:wdxk6cxs5jdntc4dfwj4lsljqq
« Previous Showing results 1 — 15 out of 1,369 results