TY - CONF
T1 - Predicting the Robustness of Undirected Network Controllability
AU - Lou, Yang
AU - He, Yaodong
AU - Wang, Lin
AU - Tsang, Kim Fung
AU - Chen, Guanrong
PY - 2020/7
Y1 - 2020/7
N2 - 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.
AB - 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.
KW - Complex network
KW - Controllability
KW - Convolutional neural network
KW - Performance prediction.
KW - Robustness
KW - Complex network
KW - Controllability
KW - Convolutional neural network
KW - Performance prediction.
KW - Robustness
KW - Complex network
KW - Controllability
KW - Convolutional neural network
KW - Performance prediction.
KW - Robustness
UR - https://cms.amss.ac.cn/conferences/ccc20/program/CCC2020_FinalProgram-Web-0722.pdf
UR - https://cms.amss.ac.cn/conferences/ccc20/program/
UR - http://www.scopus.com/inward/record.url?scp=85091395099&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85091395099&origin=recordpage
U2 - 10.23919/CCC50068.2020.9189097
DO - 10.23919/CCC50068.2020.9189097
M3 - 31A_Invited conference paper (refereed items)
SP - 4550
EP - 4553
T2 - 第三十九届中国控制会议 - The 39th Chinese Control Conference (CCC2020)
Y2 - 27 July 2020 through 29 July 2020
ER -