Predicting the Robustness of Undirected Network Controllability

Yang LOU, Yaodong HE, Lin WANG, Kim Fung TSANG, Guanrong CHEN

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the 39th Chinese Control Conference, CCC 2020
EditorsJun FU, Jian SUN
PublisherIEEE Computer Society
Pages4550-4553
Number of pages4
ISBN (Electronic)9789881563903
ISBN (Print)9781728165233
DOIs
Publication statusPublished - Jul 2020
Externally publishedYes
Event39th Chinese Control Conference, CCC 2020 - Shenyang, China
Duration: 27 Jul 202029 Jul 2020

Publication series

NameChinese Control Conference, CCC
Volume2020-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference39th Chinese Control Conference, CCC 2020
Country/TerritoryChina
CityShenyang
Period27/07/2029/07/20

Bibliographical note

Funding Information:
This work is supported by the Hong Kong ITF Grant CityU ITP/058/17LP, the National Natural Science Foundation of China under Grant No. 61873167, and the Natural Science Foundation of Shanghai (No. 17ZR1445200).

Publisher Copyright:
© 2020 Technical Committee on Control Theory, Chinese Association of Automation.

Keywords

  • Complex network
  • Controllability
  • Convolutional neural network
  • Performance prediction.
  • Robustness

Fingerprint

Dive into the research topics of 'Predicting the Robustness of Undirected Network Controllability'. Together they form a unique fingerprint.

Cite this