Total variation based community detection using a nonlinear optimization approach

Maximizing the modularity of a network is a successful tool to identify an important community of nodes. However, this combinatorial optimization problem is known to be NP-complete. Inspired by recent nonlinear modularity eigenvector approaches, we introduce the modularity total variation $TV_Q$ and show that its box-constrained global maximum coincides with the maximum of the original discrete modularity function. Thus we describe a new nonlinear optimization approach to solve the equivalent problem leading to a community detection strategy based on $TV_Q$. The proposed approach relies on the use of a fast first-order method that embeds a tailored active-set strategy. We report extensive numerical comparisons with standard matrix-based approaches and the Generalized RatioDCA approach for nonlinear modularity eigenvectors, showing that our new method compares favourably with state-of-the-art alternatives.

[1]  Mason A. Porter,et al.  A Method Based on Total Variation for Network Modularity Optimization Using the MBO Scheme , 2013, SIAM J. Appl. Math..

[2]  L. Grippo,et al.  A class of nonmonotone stabilization methods in unconstrained optimization , 1991 .

[3]  Matthias Hein,et al.  Clustering Signed Networks with the Geometric Mean of Laplacians , 2016, NIPS.

[4]  Mason A. Porter,et al.  Communities in Networks , 2009, ArXiv.

[5]  Santo Fortunato,et al.  Community detection in graphs , 2009, ArXiv.

[6]  M. Newman,et al.  Finding community structure in very large networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  R. Guimerà,et al.  Modularity from fluctuations in random graphs and complex networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Ulrik Brandes,et al.  On Modularity Clustering , 2008, IEEE Transactions on Knowledge and Data Engineering.

[9]  L. Grippo,et al.  A class of continuously differentiable exact penalty function algorithms for nonlinear programming problems , 1984 .

[10]  Carl T. Bergstrom,et al.  The map equation , 2009, 0906.1405.

[11]  Charu C. Aggarwal,et al.  Graph Clustering , 2010, Encyclopedia of Machine Learning and Data Mining.

[12]  Antonin Chambolle,et al.  A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging , 2011, Journal of Mathematical Imaging and Vision.

[13]  Dario Fasino,et al.  An Algebraic Analysis of the Graph Modularity , 2013, SIAM J. Matrix Anal. Appl..

[14]  William W. Hager,et al.  A New Active Set Algorithm for Box Constrained Optimization , 2006, SIAM J. Optim..

[15]  A. Arenas,et al.  Community detection in complex networks using extremal optimization. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  J. Hopfield,et al.  From molecular to modular cell biology , 1999, Nature.

[17]  Stefano Lucidi,et al.  A Two-Stage Active-Set Algorithm for Bound-Constrained Optimization , 2016, Journal of Optimization Theory and Applications.

[18]  Daniel P. Robinson,et al.  A globally convergent primal-dual active-set framework for large-scale convex quadratic optimization , 2015, Comput. Optim. Appl..

[19]  Desmond J. Higham,et al.  A Nonlinear Spectral Method for Core-Periphery Detection in Networks , 2018, SIAM J. Math. Data Sci..

[20]  Xueqi Cheng,et al.  Spectral methods for the detection of network community structure: a comparative analysis , 2010, ArXiv.

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

[22]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[23]  Dario Fasino,et al.  Generalized modularity matrices , 2015, ArXiv.

[24]  Xavier Bresson,et al.  Multiclass Total Variation Clustering , 2013, NIPS.

[25]  V A Traag,et al.  Narrow scope for resolution-limit-free community detection. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[26]  Matteo Cinelli,et al.  Network constraints on the mixing patterns of binary node metadata , 2019, Physical review. E.

[27]  Matthias Hein,et al.  Community detection in networks via nonlinear modularity eigenvectors , 2017, SIAM J. Appl. Math..

[28]  Matthias Hein,et al.  Beyond Spectral Clustering - Tight Relaxations of Balanced Graph Cuts , 2011, NIPS.

[29]  José Mario Martínez,et al.  Large-Scale Active-Set Box-Constrained Optimization Method with Spectral Projected Gradients , 2002, Comput. Optim. Appl..

[30]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[31]  S. Lucidi,et al.  Quadratically and superlinearly convergent algorithms for the solution of inequality constrained minimization problems , 1995 .

[32]  Santo Fortunato,et al.  Community detection in networks: A user guide , 2016, ArXiv.

[33]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[34]  Christos Faloutsos,et al.  Graphs over time: densification laws, shrinking diameters and possible explanations , 2005, KDD '05.

[35]  Matthias Hein,et al.  Spectral clustering based on the graph p-Laplacian , 2009, ICML '09.

[36]  Paul T. Boggs,et al.  Sequential Quadratic Programming , 1995, Acta Numerica.

[37]  Matthias Hein,et al.  The Power Mean Laplacian for Multilayer Graph Clustering , 2018, AISTATS.

[38]  Matthias Hein,et al.  An Inverse Power Method for Nonlinear Eigenproblems with Applications in 1-Spectral Clustering and Sparse PCA , 2010, NIPS.

[39]  José Mario Martínez,et al.  Second-order negative-curvature methods for box-constrained and general constrained optimization , 2010, Comput. Optim. Appl..

[40]  Peter Sanders,et al.  Advanced Coarsening Schemes for Graph Partitioning , 2012, ACM J. Exp. Algorithmics.

[41]  Andrea Grosso,et al.  A Population-based Approach for Hard Global Optimization Problems based on Dissimilarity Measures , 2007, Math. Program..

[42]  Francis R. Bach,et al.  Learning with Submodular Functions: A Convex Optimization Perspective , 2011, Found. Trends Mach. Learn..

[43]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[44]  Xue-Cheng Tai,et al.  Simplified Energy Landscape for Modularity Using Total Variation , 2017, SIAM J. Appl. Math..

[45]  Benjamin H. Good,et al.  Performance of modularity maximization in practical contexts. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[46]  Roger Fletcher,et al.  On the Barzilai-Borwein Method , 2005 .

[47]  M. Newman,et al.  Finding community structure in networks using the eigenvectors of matrices. , 2006, Physical review. E, Statistical, nonlinear, and soft matter physics.

[48]  Robert H. Leary,et al.  Global Optimization on Funneling Landscapes , 2000, J. Glob. Optim..

[49]  Matthias Hein,et al.  A nodal domain theorem and a higher-order Cheeger inequality for the graph $p$-Laplacian , 2016, Journal of Spectral Theory.

[50]  Christian Kirches,et al.  qpOASES: a parametric active-set algorithm for quadratic programming , 2014, Mathematical Programming Computation.

[51]  L. Grippo,et al.  A nonmonotone line search technique for Newton's method , 1986 .

[52]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[53]  Christos Faloutsos,et al.  Graph evolution: Densification and shrinking diameters , 2006, TKDD.

[54]  Cristopher Moore,et al.  Scalable detection of statistically significant communities and hierarchies, using message passing for modularity , 2014, Proceedings of the National Academy of Sciences.

[55]  Ulrik Brandes,et al.  On Finding Graph Clusterings with Maximum Modularity , 2007, WG.

[56]  Andrea Lancichinetti,et al.  Community detection algorithms: a comparative analysis: invited presentation, extended abstract , 2009, VALUETOOLS.

[57]  Hasan Davulcu,et al.  Community detection in political Twitter networks using Nonnegative Matrix Factorization methods , 2016, 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[58]  Gianni Di Pillo,et al.  An active set feasible method for large-scale minimization problems with bound constraints , 2012, Computational Optimization and Applications.