Abstract
Dismantling of complex networks is a problem to find a minimal set of nodes in which the removal leaves the network broken into connected components of sub-extensive size. It has a wide spectrum of important applications, including network immunization and network destruction. Due to its NP-hard computational complexity, this problem cannot be solved exactly with polynomial time. Traditional solutions, including manually-designed and considerably sub-optimal heuristic algorithms, and accurate message-passing ones, all suffer from low efficiency in large-scale problems. In this paper, we introduce a simple learning-based approach, CoreGQN, which seeks to train an agent that is able to smartly choose nodes that would accumulate the maximum rewards. CoreGQN is trained by hundreds of thousands self-plays on small synthetic graphs, and can then be able to generalize well on real-world networks across different types with different scales. Extensive experiments demonstrate that CoreGQN performs on par with the state-of-art algorithms at greatly reduced computational costs, suggesting that CoreGQN should be the better choice for practical network dismantling purposes.
Similar content being viewed by others
References
Albert R, Barabási AL (2002) Statistical mechanics of complex networks. Rev Mod Phys 74(1):47
Altarelli F, Braunstein A, Dall’Asta L, Zecchina R (2013) Large deviations of cascade processes on graphs. Phys Rev E 87(6):062,115
Altarelli F, Braunstein A, Dall’Asta L, Zecchina R (2013) Optimizing spread dynamics on graphs by message passing. J Stat Mech Theory Exp 2013(09):P09,011
Barabási AL, Albert R (1999) Emergence of scaling in random networks. Science 286(5439):509–512
Bavelas A (1950) Communication patterns in task-oriented groups. J Acoust Soc Am 22(6):725–730
Bello I, Pham H, Le QV, Norouzi M, Bengio S (2016) Neural combinatorial optimization with reinforcement learning. arXiv:1611.09940
Braunstein A, Dall’Asta L, Semerjian G, Zdeborová L (2016) Network dismantling. Proc Natl Acad Sci 113(44):12368–12373
Brin S, Page L (1998) The anatomy of a large-scale hypertextual web search engine. Comput Netw ISDN Syst 30(1–7):107–117
Clusella P, Grassberger P, Pérez-Reche FJ, Politi A (2016) Immunization and targeted destruction of networks using explosive percolation. Phys Rev Lett 117(20):208,301
Cohen R, Erez K, Ben-Avraham D, Havlin S (2001) Breakdown of the internet under intentional attack. Phys Rev Lett 86(16):3682
Dai H, Dai B, Song L (2016) Discriminative embeddings of latent variable models for structured data. In: International conference on machine learning, pp 2702–2711
Fan C, Liu Z, Lu X, Xiu B, Chen Q (2017) An efficient link prediction index for complex military organization. Physica A Stat Mech Appl 469:572–587
Fan C, Sun Y, Zeng L, Liu YY, Chen M, Liu Z (2019) Dismantle large networks through deep reinforcement learning. In: ICLR representation learning on graphs and manifolds workshop
Fan C, Xiao K, Xiu B, Lv G (2014) A fuzzy clustering algorithm to detect criminals without prior information. In: Proceedings of the 2014 IEEE/ACM international conference on advances in social networks analysis and mining, pp 238–243. IEEE Press
Fan C, Zeng L, Ding Y, Chen M, Sun Y, Liu Z (2019) Learning to identify high betweenness centrality nodes from scratch: A novel graph neural network approach. arXiv:1905.10418
Freeman LC (1977) A set of measures of centrality based on betweenness. Sociometry 40:35–41
Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Advances in neural information processing systems, pp 1024–1034
Hessel M, Modayil J, Van Hasselt H, Schaul T, Ostrovski G, Dabney W, Horgan D, Piot B, Azar M, Silver D (2018) Rainbow: combining improvements in deep reinforcement learning. In: Thirty-Second AAAI conference on artificial intelligence
Janson S, Thomason A (2008) Dismantling sparse random graphs. Comb Probab Comput 17(2):259–264
Kempe D, Kleinberg J, Tardos É (2003) Maximizing the spread of influence through a social network. In: Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 137–146. ACM
Khalil E, Dai H, Zhang Y, Dilkina B, Song L (2017) Learning combinatorial optimization algorithms over graphs. In: Advances in neural information processing systems, pp 6348–6358
Kunegis J (2013) Konect: the koblenz network collection. In: Proceedings of the 22nd international conference on world wide web, pp 1343–1350. ACM
Leskovec J, Kleinberg J, Faloutsos C (2007) Graph evolution: densification and shrinking diameters. ACM Trans Knowl Discov Data 1(1):2
Leskovec J, Lang KJ, Dasgupta A, Mahoney MW (2009) Community structure in large networks: natural cluster sizes and the absence of large well-defined clusters. Internet Math 6(1):29–123
Li Z, Chen Q, Koltun V (2018) Combinatorial optimization with graph convolutional networks and guided tree search. In: Advances in neural information processing systems, pp 539–548
Ma Z, Li M, Wang Y (2019) Pan: Path integral based convolution for deep graph neural networks
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529
Morone F, Makse HA (2015) Influence maximization in complex networks through optimal percolation. Nature 524(7563):65
Mugisha S, Zhou HJ (2016) Identifying optimal targets of network attack by belief propagation. Phys Rev E 94(1):012,305
Pastor-Satorras R, Vespignani A (2001) Epidemic spreading in scale-free networks. Phys Rev Lett 86(14):3200
Ren XL, Gleinig N, Helbing D, Antulov-Fantulin N (2019) Generalized network dismantling. In: Proceedings of the national academy of sciences, p 201806108
Schneider CM, Moreira AA, Andrade JS, Havlin S, Herrmann HJ (2011) Mitigation of malicious attacks on networks. Proc Natl Acad Sci 108(10):3838–3841
Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press, Cambridge
Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. In: ICLR
Zdeborová L, Zhang P, Zhou HJ (2016) Fast and simple decycling and dismantling of networks. Sci Rep 6:37,954
Zhou HJ (2013) Spin glass approach to the feedback vertex set problem. Eur Phys J B 86(11):455
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fan, C., Zeng, L., Feng, Y. et al. A novel learning-based approach for efficient dismantling of networks. Int. J. Mach. Learn. & Cyber. 11, 2101–2111 (2020). https://doi.org/10.1007/s13042-020-01104-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-020-01104-8