Predicting the Robustness of Undirected Network Controllability

Robustness of the network controllability reflects how well a networked system can maintain its controllability against destructive attacks. The measure of the network controllability robustness is quantified by a sequence of values that record the remaining controllability of the network after a sequence of node-removal or edge-removal attacks. Traditionally, the controllability robustness is determined by attack simulations, which is computationally time consuming. In this paper, an improved method for predicting the controllability robustness of undirected networks is developed based on machine learning using a convolutional neural network. This approach is motivated by the following observations: 1) there is no clear correlation between the topological features and the controllability robustness of a general undirected network, 2) the adjacency matrix of a network can be represented as a gray-scale image, 3) the convolutional neural network technique has proved successful in image processing without human intervention. In the new framework, preprocessing and filtering are embedded, and a sufficiently large number of training datasets generated by simulations are used to train several convolutional neural networks for classification and prediction, respectively. Extensive experimental studies were carried out, which demonstrate that the proposed framework for predicting the controllability robustness of undirected networks is more accurate and reliable than the conventional single convolutional neural network predictor.

[1]  Lin Wang,et al.  Toward Stronger Robustness of Network Controllability: A Snapback Network Model , 2018, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Albert-László Barabási,et al.  Effect of correlations on network controllability , 2012, Scientific Reports.

[3]  S. Havlin,et al.  The extreme vulnerability of interdependent spatially embedded networks , 2012, Nature Physics.

[4]  Guanrong Chen,et al.  Controllability of networked higher-dimensional systems with one-dimensional communication , 2017, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[5]  Derek Ruths,et al.  Robustness of Network Controllability under Edge Removal , 2013, CompleNet.

[6]  Albert-László Barabási,et al.  Control Centrality and Hierarchical Structure in Complex Networks , 2012, PloS one.

[7]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[8]  Hiroki Sayama,et al.  Optimization of robustness and connectivity in complex networks. , 2003, Physical review letters.

[9]  Ginestra Bianconi,et al.  Network controllability is determined by the density of low in-degree and out-degree nodes. , 2014, Physical review letters.

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

[11]  Guanrong Chen,et al.  Enhancing Controllability Robustness of q-Snapback Networks through Redirecting Edges , 2019, Research.

[12]  Wen-Xu Wang,et al.  Exact controllability of complex networks , 2013, Nature Communications.

[13]  白亮,et al.  Optimization of robustness of network controllability against malicious attacks , 2014 .

[14]  Hans J. Herrmann,et al.  Mitigation of malicious attacks on networks , 2011, Proceedings of the National Academy of Sciences.

[15]  Albert-László Barabási,et al.  Control Principles of Complex Networks , 2015, ArXiv.

[16]  Albert-László Barabási,et al.  Controllability of complex networks , 2011, Nature.

[17]  M. Newman,et al.  Renormalization Group Analysis of the Small-World Network Model , 1999, cond-mat/9903357.

[18]  Ying-Cheng Lai,et al.  Physical controllability of complex networks , 2017, Scientific Reports.

[19]  P. ERDbS.  ON THE STRENGTH OF CONNECTEDNESS OF A RANDOM GRAPH , 2001 .

[20]  Guanrong Chen,et al.  Advances in Network Controllability , 2019, IEEE Circuits and Systems Magazine.

[21]  Guanrong Chen,et al.  Predicting Network Controllability Robustness: A Convolutional Neural Network Approach , 2020, IEEE transactions on cybernetics.

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

[23]  Beom Jun Kim,et al.  Attack vulnerability of complex networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[24]  Yuan Zhang,et al.  Controllability Analysis for a Networked Dynamic System With Autonomous Subsystems , 2017, IEEE Transactions on Automatic Control.

[25]  Lin Wang,et al.  Controllability of networked MIMO systems , 2015, Autom..

[26]  Xiang Li,et al.  Fundamentals of Complex Networks: Models, Structures and Dynamics , 2015 .