Machine learning meets complex networks via coalescent embedding in the hyperbolic space

Complex network topologies and hyperbolic geometry seem specularly connected (Papadopoulos et al. 2012), and one of the most fascinating and challenging problems of recent complex network theory is to map a given network to its hyperbolic space. The Popularity Similarity Optimization (PSO) model represents-at the moment-the climax of this theory (Papadopoulos et al. 2012). It suggests that the trade-off between node popularity and similarity is a mechanism to explain how complex network topologies emerge-as discrete samples-from the continuous world of hyperbolic geometry (Papadopoulos et al. 2015). The hyperbolic space seems appropriate to represent real complex networks. In fact, it preserves many of their fundamental topological properties, and can be exploited for real applications such as, among others, link prediction and community detection. Here, we observe for the first time that a topological-based machine learning class of algorithms-for nonlinear unsupervised dimensionality reduction-can directly approximate the network's node angular coordinates of the hyperbolic model into a two-dimensional space, according to a similar topological organization that we named angular coalescence. On the basis of this phenomenon, we propose a new class of algorithms that offers fast and accurate coalescent embedding of networks in the hyperbolic space even for graphs with thousands of nodes.

[1]  W. Zachary,et al.  An Information Flow Model for Conflict and Fission in Small Groups , 1977, Journal of Anthropological Research.

[2]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[3]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[4]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[5]  Pablo M. Gleiser,et al.  Community Structure in Jazz , 2003, Adv. Complex Syst..

[6]  M. Newman,et al.  Identifying the role that animals play in their social networks , 2004, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[7]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[8]  Marián Boguñá,et al.  Navigability of Complex Networks , 2007, ArXiv.

[9]  Desmond J. Higham,et al.  Fitting a geometric graph to a protein-protein interaction network , 2008, Bioinform..

[10]  Desmond J. Higham,et al.  Geometric De-noising of Protein-Protein Interaction Networks , 2009, PLoS Comput. Biol..

[11]  Trey Ideker,et al.  Nonlinear dimension reduction and clustering by Minimum Curvilinearity unfold neuropathic pain and tissue embryological classes , 2010, Bioinform..

[12]  Marián Boguñá,et al.  Popularity versus similarity in growing networks , 2011, Nature.

[13]  Timothy Ravasi,et al.  From link-prediction in brain connectomes and protein interactomes to the local-community-paradigm in complex networks , 2013, Scientific Reports.

[14]  Carlo Vittorio Cannistraci,et al.  Minimum curvilinearity to enhance topological prediction of protein interactions by network embedding , 2013, Bioinform..

[15]  Dmitri V. Krioukov,et al.  Network Mapping by Replaying Hyperbolic Growth , 2012, IEEE/ACM Transactions on Networking.

[16]  Ginestra Bianconi,et al.  Complex Quantum Network Manifolds in Dimension d > 2 are Scale-Free , 2015, Scientific Reports.

[17]  Simone Daminelli,et al.  Common neighbours and the local-community-paradigm for topological link prediction in bipartite networks , 2015, ArXiv.

[18]  Ginestra Bianconi,et al.  Interdisciplinary and physics challenges of network theory , 2015, 1509.00345.

[19]  Linyuan Lü,et al.  Toward link predictability of complex networks , 2015, Proceedings of the National Academy of Sciences.

[20]  Qingguang Li,et al.  Link prediction based on hyperbolic mapping with community structure for complex networks , 2016 .