Community Detection: Exact Recovery in Weighted Graphs

In community detection, the exact recovery of communities (clusters) has been mainly investigated under the general stochastic block model with edges drawn from Bernoulli distributions. This paper considers the exact recovery of communities in a complete graph in which the graph edges are drawn from either a set of Gaussian distributions with community-dependent means and variances, or a set of exponential distributions with community-dependent means. For each case, we introduce a new semi-metric that describes sufficient and necessary conditions of exact recovery. The necessary and sufficient conditions are asymptotically tight. The analysis is also extended to incomplete, fully connected weighted graphs.

[1]  Agata Fronczak,et al.  Exponential random graph models for networks with community structure , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Emmanuel Abbe,et al.  Community Detection in General Stochastic Block models: Fundamental Limits and Efficient Algorithms for Recovery , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[3]  Yiannis Kompatsiaris,et al.  Community detection in Social Media , 2012, Data Mining and Knowledge Discovery.

[4]  Alexandre Proutière,et al.  Community Detection via Random and Adaptive Sampling , 2014, COLT.

[5]  Sivaraman Balakrishnan,et al.  Minimax Localization of Structural Information in Large Noisy Matrices , 2011, NIPS.

[6]  Jiaming Xu,et al.  Statistical Problems with Planted Structures: Information-Theoretical and Computational Limits , 2018, Information-Theoretic Methods in Data Science.

[7]  Angelo Bifone,et al.  Community detection in weighted brain connectivity networks beyond the resolution limit , 2016, NeuroImage.

[8]  Aria Nosratinia,et al.  EXIT analysis for belief propagation in degree-correlated stochastic block models , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[9]  Santo Fortunato,et al.  Detection of gene communities in multi-networks reveals cancer drivers , 2015, Scientific Reports.

[10]  Elchanan Mossel,et al.  Density Evolution in the Degree-correlated Stochastic Block Model , 2015, COLT.

[11]  Elizaveta Levina,et al.  On semidefinite relaxations for the block model , 2014, ArXiv.

[12]  Bruce Hajek,et al.  Information limits for recovering a hidden community , 2015, 2016 IEEE International Symposium on Information Theory (ISIT).

[13]  Elchanan Mossel,et al.  A Proof of the Block Model Threshold Conjecture , 2013, Combinatorica.

[14]  Aria Nosratinia,et al.  Exact Recovery by Semidefinite Programming in the Binary Stochastic Block Model with Partially Revealed Side Information , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Aria Nosratinia,et al.  Community Detection with Secondary Latent Variables , 2020, 2020 IEEE International Symposium on Information Theory (ISIT).

[16]  P. Rigollet,et al.  Optimal detection of sparse principal components in high dimension , 2012, 1202.5070.

[17]  Yonggang Wen,et al.  Algorithms and Applications for Community Detection in Weighted Networks , 2015, IEEE Transactions on Parallel and Distributed Systems.

[18]  Aria Nosratinia,et al.  Community Detection with Side Information via Semidefinite Programming , 2019, 2019 IEEE International Symposium on Information Theory (ISIT).

[19]  Yudong Chen,et al.  Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices , 2014, J. Mach. Learn. Res..

[20]  Laurent Massoulié,et al.  Community detection thresholds and the weak Ramanujan property , 2013, STOC.

[21]  Emmanuel Abbe,et al.  Community detection and stochastic block models: recent developments , 2017, Found. Trends Commun. Inf. Theory.

[22]  Emmanuel Abbe,et al.  Exact Recovery in the Stochastic Block Model , 2014, IEEE Transactions on Information Theory.

[23]  Kathryn B. Laskey,et al.  Stochastic blockmodels: First steps , 1983 .

[24]  Elchanan Mossel,et al.  Consistency Thresholds for the Planted Bisection Model , 2014, STOC.

[25]  Bruce E. Hajek,et al.  Exact recovery threshold in the binary censored block model , 2015, 2015 IEEE Information Theory Workshop - Fall (ITW).

[26]  Yu. I. Ingster,et al.  Sharp Variable Selection of a Sparse Submatrix in a High-Dimensional Noisy Matrix , 2013, 1303.5647.

[27]  Elchanan Mossel,et al.  Belief propagation, robust reconstruction and optimal recovery of block models , 2013, COLT.

[28]  Bruce E. Hajek,et al.  Achieving exact cluster recovery threshold via semidefinite programming , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[29]  Florent Krzakala,et al.  Spectral detection in the censored block model , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[30]  Elchanan Mossel,et al.  Reconstruction and estimation in the planted partition model , 2012, Probability Theory and Related Fields.