Approximating Network Centrality Measures Using Node Embedding and Machine Learning

Extracting information from real-world large networks is a key challenge nowadays. For instance, computing a node centrality may become unfeasible depending on the intended centrality due to its computational cost. One solution is to develop fast methods capable of approximating network centralities. Here, we propose an approach for efficiently approximating node centralities for large networks using Neural Networks and Graph Embedding techniques. Our proposed model, entitled Network Centrality Approximation using Graph Embedding (NCA-GE), uses the adjacency matrix of a graph and a set of features for each node (here, we use only the degree) as input and computes the approximate desired centrality rank for every node. NCA-GE has a time complexity of $O(|E|)$, $E$ being the set of edges of a graph, making it suitable for large networks. NCA-GE also trains pretty fast, requiring only a set of a thousand small synthetic scale-free graphs (ranging from 100 to 1000 nodes each), and it works well for different node centralities, network sizes, and topologies. Finally, we compare our approach to the state-of-the-art method that approximates centrality ranks using the degree and eigenvector centralities as input, where we show that the NCA-GE outperforms the former in a variety of scenarios.

[1]  Lisandro Zambenedetti Granville,et al.  Machine Learning in Network Centrality Measures , 2018, ACM Comput. Surv..

[2]  Jure Leskovec,et al.  {SNAP Datasets}: {Stanford} Large Network Dataset Collection , 2014 .

[3]  Walid Saad,et al.  Centrality-Based Caching for Mobile Wireless Networks , 2014 .

[4]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[5]  Renato Lo Cigno,et al.  Pop-routing: Centrality-based tuning of control messages for faster route convergence , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[6]  Luís C. Lamb,et al.  On approximating networks centrality measures via neural learning algorithms , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[7]  Sebastiano Vigna,et al.  Axioms for Centrality , 2013, Internet Math..

[8]  Palash Goyal,et al.  dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning , 2018, Knowl. Based Syst..

[9]  Christian Staudt,et al.  Approximating Betweenness Centrality in Large Evolving Networks , 2014, ALENEX.

[10]  R. Forthofer,et al.  Rank Correlation Methods , 1981 .

[11]  Palash Goyal,et al.  Graph Embedding Techniques, Applications, and Performance: A Survey , 2017, Knowl. Based Syst..

[12]  Andrew G. Barto,et al.  Betweenness Centrality as a Basis for Forming Skills Özgür Şimşek , 2007 .

[13]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[14]  David A. Bader,et al.  Approximating Betweenness Centrality , 2007, WAW.

[15]  Olaf Sporns,et al.  Complex network measures of brain connectivity: Uses and interpretations , 2010, NeuroImage.

[16]  Miguel Correia,et al.  Betweenness centrality in Delay Tolerant Networks: A survey , 2015, Ad Hoc Networks.

[17]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[18]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[19]  David A. Bader,et al.  Parallel Algorithms for Evaluating Centrality Indices in Real-world Networks , 2006, 2006 International Conference on Parallel Processing (ICPP'06).

[20]  André da Motta Salles Barreto,et al.  Graph-Based Skill Acquisition For Reinforcement Learning , 2019, ACM Comput. Surv..

[21]  Artur Ziviani,et al.  A Multilayer and Time-Varying Structural Analysis of the Brazilian Air Transportation Network , 2017, LADaS@VLDB.

[22]  Yingjie Sun,et al.  Network Analysis of US Air Transportation Network , 2010, Data Mining for Social Network Data.

[23]  Parham Moradi,et al.  Automatic skill acquisition in Reinforcement Learning using connection graph stability centrality , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[24]  Parham Moradi,et al.  Automatic Skill Acquisition in Reinforcement Learning Agents Using Connection Bridge Centrality , 2010, FGIT-FGCN.

[25]  Le Song,et al.  Discriminative Embeddings of Latent Variable Models for Structured Data , 2016, ICML.

[26]  Jure Leskovec,et al.  Representation Learning on Graphs: Methods and Applications , 2017, IEEE Data Eng. Bull..

[27]  Alex Borges Vieira,et al.  Time Centrality in Dynamic Complex Networks , 2015, Adv. Complex Syst..

[28]  Ulrik Brandes,et al.  Centrality Estimation in Large Networks , 2007, Int. J. Bifurc. Chaos.

[29]  Kazushi Sano,et al.  Explaining Traffic Flow Patterns Using Centrality Measures , 2015 .

[30]  Kevin Chen-Chuan Chang,et al.  A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications , 2017, IEEE Transactions on Knowledge and Data Engineering.

[31]  Ying Ding,et al.  Applying centrality measures to impact analysis: A coauthorship network analysis , 2009, J. Assoc. Inf. Sci. Technol..

[32]  George Cybenko,et al.  Approximating centrality in evolving graphs: toward sublinearity , 2017, Defense + Security.

[33]  Yong Gao,et al.  Understanding Urban Traffic-Flow Characteristics: A Rethinking of Betweenness Centrality , 2013 .

[34]  Madhumangal Pal,et al.  Study on centrality measures in social networks: a survey , 2018, Social Network Analysis and Mining.

[35]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[36]  Wenwu Zhu,et al.  Structural Deep Network Embedding , 2016, KDD.

[37]  V. Latora,et al.  A measure of centrality based on network efficiency , 2004, cond-mat/0402050.

[38]  Luís C. Lamb,et al.  Estimating complex networks centrality via neural networks and machine learning , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[39]  Le Song,et al.  2 Common Formulation for Greedy Algorithms on Graphs , 2018 .

[40]  Clémence Magnien,et al.  Time evolution of the importance of nodes in dynamic networks , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[41]  Edith Cohen,et al.  Computing classic closeness centrality, at scale , 2014, COSN '14.

[42]  David Eppstein,et al.  Fast approximation of centrality , 2000, SODA '01.

[43]  Evgenios M. Kornaropoulos,et al.  Fast approximation of betweenness centrality through sampling , 2014, Data Mining and Knowledge Discovery.

[44]  Alan M. Frieze,et al.  Random graphs , 2006, SODA '06.

[45]  Negin Samadi,et al.  A new centrality measure based on the negative and positive effects of clustering coefficient for identifying influential spreaders in complex networks , 2018 .

[46]  Wei Xiong,et al.  Active learning for protein function prediction in protein-protein interaction networks , 2013, Neurocomputing.

[47]  Negin Samadi,et al.  A new local and multidimensional ranking measure to detect spreaders in social networks , 2018, Computing.

[48]  James A. Danowski,et al.  Automatic Mapping of Social Networks of Actors from Text Corpora: Time Series Analysis , 2009, 2009 International Conference on Advances in Social Network Analysis and Mining.

[49]  Andrew Seary,et al.  Eigen Analysis of Networks , 2000, J. Soc. Struct..

[50]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

[51]  Chao Wang,et al.  What if wireless routers were social? approaching wireless mesh networks from a social networks perspective , 2012, IEEE Wireless Communications.

[52]  Jian Pei,et al.  A Survey on Network Embedding , 2017, IEEE Transactions on Knowledge and Data Engineering.

[53]  Mehdi Bennis,et al.  Living on the edge: The role of proactive caching in 5G wireless networks , 2014, IEEE Communications Magazine.