为了应对这些挑战,研究人员将拓扑数据分析(topological data analysis,TDA)的概念引入到复杂的多层网络的研究中,并提出了一种网络聚类的拓扑方法。TDA是代数拓扑和数据科学[31-34]的一种新兴方法,它提供了一种数学上严格的机制来分析数据形状。尤其是,TDA允许人们分析观察数据的拓扑和几何特性,从而更深入地了解数据生成过程背后的隐藏机制。[35-38] 拓扑网络聚类背后的关键思想是根据近邻节点形状相似程度对其进行分组。特别是,该算法使用拓扑方法基于持续性图对每个节点周围的局部拓扑和几何进行比较,因此被称为“使用持续性图的聚类”(CPD)。CPD方法既可以系统地计算网络层内部和网络层之间的异构高阶特性,又可以集成来自近邻节点及其相互作用的重要信息。[39-41] 研究人员说明了他们的CPD算法的应用以及拓扑概念在复杂网络聚类中的实用性。他们以多层网络在房屋保险中为例进行说明。研究人员通过引入基于气候条件和房屋保险变量的多层复杂网络,基于拓扑CPD方法对房屋进行分区。与基于简单地理邻近度的传统工具相比,基于环境和社会人口统计学特征相似度的风险图可以更准确地模拟气候风险。
1.S. Caschili, F. R. Medda, A. Wilson, An interdependent multi-layer model: Resilience of international networks. Netw. Spatial Econ. 15, 313–335 (2015).2.S.Pilosof,M.A.Porter,M.Pascual,S.Ke ́fi,Themultilayernatureofecological networks. Nat. Ecol. Evol. 1, 101 (2017).3. M. Pedersen, A. Zalesky, A. Omidvarnia, G. D. Jackson, Multilayer network switching rate predicts brain performance. Proc. Natl. Acad. Sci. U.S.A. 115, 13376–13381 (2018).4. M. Wu et al., A tensor-based framework for studying eigenvector multicentrality inmultilayer networks. Proc. Natl. Acad. Sci. U.S.A. 116, 15407–15413 (2019).5.C.Gomez,A.D.Gonza ́lez,H.Baroud,C.D.Bedoya-Motta,Integratingoperational and organizational aspects in interdependent infrastructure network recovery. RiskAnal. 39, 1913–1929 (2019).6. F. Messina et al., COVID-19: Viral–host interactome analyzed by network based-approach model to study pathogenesis of SARS-CoV-2 infection. J. Transl. Med. 18,1–10 (2020).7. Z. Kosowska-Stamirowska, Network effects govern the evolution of maritime trade.Proc. Natl. Acad. Sci. U.S.A. 117, 12719–12728 (2020).8. L. Tang, K. Jing, J. He, H. Stanley, Complex interdependent supply chain networks:Cascading failure and robustness. Phys. Stat. Mech. Appl. 443, 58–69 (2015).9. H. Baroud, K. Barker, J. E. Ramirez-Marquez, C. M. Rocco, Inherent costs and inter- dependent impacts of infrastructure network resilience. Risk Anal. 35, 642–662(2015).10. I. Bermudez et al., Twitter response to Munich July 2016 attack: Network analysis ofinfluence. Front. Big Data 2, 17 (2019).11. Q. Li, S. Dong, A. Mostafavi, Modeling of inter-organizational coordination dynam-ics in resilience planning of infrastructure systems: A multilayer network simulationframework. PloS One 14, e0224522 (2019).12. E. Nosyreva, L. Massel, “Application of multilayer networks to detect critical energyfacilities” in Proceedings of the VIth International Workshop ‘Critical Infrastructures: Contingency Management, Intelligent, Agent-Based, Cloud Computing and Cyber Security’(IWCI2019),L.Massel,N.Makagonova,A.Kopaygorodsky,A.Massel,Eds. (Atlantis Press, 2019), pp. 249–256.13. I. Bachmann, J. Bustos, B. Bustos, A survey on frameworks used for robustness analysis on interdependent networks. Complexity 2020, 1–17 (2020).14. N. Yadav, S. Chatterjee, A. Ganguly, Resilience of urban transport network-of- networks under intense flood hazards exacerbated by targeted attacks. Sci. Rep. 10, 10350(2020).15. T. Wang, M. Brede, A. Ianni, E. Mentzakis, Characterizing dynamic communication in online eating disorder communities: A multiplex network approach. Appl. Netw. Sci. 4, 12 (2019).16. P. V. Bindu, R. Mishra, P. Thilagam, Discovering spammer communities in Twitter. J. Intell. Inf. Syst. 51, 503–527 (2018).17. M. Wu et al., A tensor-based framework for studying eigenvector multicentrality in multilayer networks. Proc. Natl. Acad. Sci. U.S.A. 116, 15407–15413 (2019).18. R. Interdonato, M. Magnani, D. Perna, A. Tagarelli, D. Vega, Multilayer network simplification: Approaches, models and methods. Comput. Sci. Rev. 36, 100246 (2020).19. A. Tagarelli, A. Amelio, F. Gullo, Ensemble-based community detection in multilayernetworks. Data Min. Knowl. Discov. 31, 1506–1543 (2017).20. N. Arinik, R. Figueiredo, V. Labatut, Multiple partitioning of multiplex signednetworks: Application to European Parliament votes. Soc. Network. 60, 83–102(2020).21.T.Valle`s-Catala`,F.A.Massucci,R.Guimera`,M.Sales-Pardo,Multilayerstochasticblockmodels reveal the multilayer structure of complex networks. Phys. Rev. X 6, 011036(2016).22. S. Paul, Y. Chen, Consistent community detection in multi-relational data throughrestricted multi-layer stochastic blockmodel. Electron. J. Statist. 10, 3807–3870 (2016).23. P. Barbillon, S. Donnet, E. Lazega, A. Bar-Hen, Stochastic block models for multiplex networks: An application to a multilevel network of researchers. J. Roy. Stat. Soc. 180,295–314 (2017).24. J. D. Wilson, J. Palowitch, S. Bhamidi, A. B. Nobel, Community extraction in multilayernetworks with heterogeneous community structure. J. Mach. Learn. Res. 18, 5458–5506 (2017).25. D. R. DeFord, S. D. Pauls, Spectral clustering methods for multiplex networks. Phys.Stat. Mech. Appl. 533, 121949 (2019).26. F. Znidi, H. Davarikia, K. Iqbal, M. Barati, Multi-layer spectral clustering approachto intentional islanding in bulk power systems. J. Mod. Power Syst. Clean Energy 7,1044–1055 (2019).27. P. Mercado, F. Tudisco, M. Hein, “Spectral clustering of signed graphs via matrix powermeans” in Proceedings of the 36th International Conference on Machine Learning, K.Chaudhuri, R. Salakhutdinov, Eds. (ML Research Press, 2019), pp. 1–11.28. S. Paul, Y. Chen, Spectral and matrix factorization methods for consistent communitydetection in multi-layer networks. Ann. Stat. 48, 230–250 (2020).29. D. J. Watts, S. H. Strogatz, Collective dynamics of ‘small-world’ networks. Nature 393, 440–442 (1998).30. A. R. Benson, D. F. Gleich, J. Leskovec, Higher-order organization of complex networks. Science 353, 163–166 (2016).31.R.Ghrist,Barcodes:Thepersistenttopologyofdata.Bull.Am.Math.Soc.45,61–75 (2008).32. G. Carlsson, Topology and data. BAMS 46, 255–308 (2009).33. F. Chazal, B. Michel, An introduction to topological data analysis: Fundamen-tal and practical aspects for data scientists. arXiv [Preprint] (2017). https://arxiv.org/abs/1710.04019 (Accessed 15 January 2020). 34.G.Carlsson,“Persistenthomologyandappliedhomotopytheory”inHandbookofHomotopy Theory, H. Miller, Ed. (CRC Press, 2019), pp. 297–330.35. P. Y. Lum et al., Extracting insights from the shape of complex data using topology.Sci. Rep. 3, 1236 (2013).36. N. Otter, M. A. Porter, U. Tillmann, P. Grindrod, H. A. Harrington, A roadmap for thecomputation of persistent homology. EPJ Data Sci. 6, 17 (2017).37. L. Wasserman, Topological data analysis. Annu. Rev. Stat. App. 5, 501–532 (2018).38. M. R. McGuirl, A. Volkening, B. Sandstede, Topological data analysis of zebrafishpatterns. Proc. Natl. Acad. Sci. U.S.A. 117, 5113–5124 (2020).39. G. Singh, F. Memoli, G. Carlsson,”Topological methods for the analysis of highdimensional data sets and 3D object recognition” in Eurographics Symposium onPoint-Based Graphics 2007 (IEEE, 2007), pp. 91–100.40. F. Chazal, L. Guibas, S. Oudot, P. Skraba, Persistence-based clustering in Riemannianmanifolds. JACM 60, 1–38 (2013).41. U. Islambekov, Y.R. Gel, Unsupervised space-time clustering using persistenthomology. Environmetrics 30, e2539 (2019).42. M. Golnaraghi, Climate Change and the Insurance Industry: Taking Action as RiskManagers and Investors (The Geneva Association, 2018).43. A. A. Tsonis, K. L. Swanson, P. J. Roebber, What do networks have to do with climate?Bull. Am. Meteorol. Soc. 87, 585–596 (2006).44. A. Gozolchiani, K. Yamasaki, O. Gazit, S. Havlin, Pattern of climate network blinkinglinksfollowsElNin ̃oevents.Europhys.Lett.83,28005(2008).45. K. Steinhaeuser, N. V. Chawla, A. R. Ganguly, An exploration of climate data usingcomplex networks. SIGKDD Explor. Newsl. 12, 25–32 (2010).46. K. Steinhaeuser, A. R Ganguly, N. V. Chawla, Multivariate and multiscale dependencein the global climate system revealed through complex networks. Clim. Dynam. 39,889–895 (2012).47.J.Ludescheretal.,VeryearlywarningofnextElNin ̃o.Proc.Natl.Acad.Sci.U.S.A. 111, 2064–2066 (2014).48.W. K. Huang, D. S. Cooley, I. Ebert-Uphoff, C. Chen, S. Chatterjee, New exploratory tools for extremal dependence: χ networks and annual extremal networks. J. Agric. Biol. Environ. Stat. 24, 484–501 (2019).49.M. Kivela ̈ et al., Multilayer networks. J. Complex Netw. 2, 203–271 (2014).50.N. Wider, A. Garas, I. Scholtes, F. Schweitzer. An ensemble perspective on multi-layer networks. arXiv [Preprint] (2015). https://arxiv.org/abs/1507.00169 (Accessed 12 March 2020).51.F. W. Takes, W. A. Kosters, W. Boyd, M. Eelke, Heemskerk, Multiplex network motifs as building blocks of corporate networks. Appl. Netw. Sci. 3, 1–22 (2018).52.J. A. Baggio et al., Multiplex social ecological network analysis reveals how social changes affect community robustness more than resource depletion. Proc. Natl. Acad. Sci. U.S.A. 113, 13708–13713 (2016).53.A.Aleta,S.Meloni,Y.Moreno,Amultilayerperspectivefortheanalysisofurban transportation systems. Sci. Rep. 7, 44359 (2017).54. T. Millington, M. Niranjan, “Quantifying influence in financial markets via partial cor- relation network inference” in 11th International Symposium on Image and Signal Processing and Analysistextit (ISPA, 2019), pp. 306–311.55. P. Giudici, G. Polinesi, Crypto price discovery through correlation networks. Ann. Oper. Res. 299, 443–457 (2019).56. D. R. Williams, P. Rast, Back to the basics: Rethinking partial correlation network methodology. Br. J. Math. Stat. Psychol. 73, 187–212 (2020).57. M. Hawrylycz et al., Multi-scale correlation structure of gene expression in the brain. Neural Netw. 24, 933–942 (2011).58. G. Petri et al., Homological scaffolds of brain functional networks. J. R. Soc. Interf. 11, 20140873 (2014).59. R. Yu et al., Weighted graph regularized sparse brain network construction for MCI identification. Pattern Recogn. 90, 220–231 (2019).60. M. Lu, U. Lall, J. Kawale, S. Liess, V. Kumar, Exploring the predictability of 30-day extreme precipitation occurrence using a global SST–SLP correlation network. J. Clim. 29, 1013–1029 (2016).61. A. Karpatne, V. Kumar, “Big data in climate: Opportunities and challenges for machine learning” in Proceedings of the 23rd ACM SIGKDD International Confer- ence on Knowledge Discovery and Data Mining, KDD ’17 (Association for Computing Machinery, New York, 2017), pp. 21–22.62. N. Ying, D. Zhou, Z. G. Han, Q. H. Chen, Q. Ye, Z. G. Xue, Rossby waves detection in the CO2 and temperature multilayer climate network. Geophys. Res. Lett. 47, e2019GL086507 (2020).63. L. Breiman, J. H. Friedman, Estimating optimal transformations for multiple regres- sion and correlation. J. Am. Stat. Assoc. 80, 580–598 (1985).64. P. Goyal, E. Ferrara, Graph embedding techniques, applications, and performance: A survey. Knowl. Base Syst. 151, 78–94 (2018).65. W. L. Hamilton, R. Ying, J. Leskovec, Representation learning on graphs: Methods and applications. arXiv [Preprint] (2017). https://arxiv.org/abs/1709.05584 (Accessed 15 January 2020).66. J. Li, C. Chen, H. Tong, H. Liu, “Multi-layered network embedding” in Proceedings of SDM18 (SIAM, 2018), pp. 684–692.67. R. G. Barcodes, The persistent topology of data. BAMS 45, 61–75 (2008).68. A. Zomorodian, Fast construction of the Vietoris–Rips complex. Comput. Graph. 34,263–271 (2010).69. X. Dong, P. Frossard, P. Vandergheynst, N. Nefedov, Clustering with multi-layergraphs: A spectral perspective. IEEE Trans. Signal Process. 60, 5820–5831 (2012).70. J. Chen, H. Molter, M. Sorge, O. Suchy`, “Cluster editing in multi-layer and temporal graphs” in 29th International Symposium on Algorithms and Computation (ISAAC 2018), W.-L. Hsu, D.-J. Lee, C.-S. Liao, Eds. (Dagstuhl Publishing, 2018), pp. 24:1–24:13.71. C. Li, G. Biswas, Unsupervised learning with mixed numeric and nominal data. IEEE Trans. Knowl. Data Eng. 14, 673–690 (2002).72. B. Stratman, S. Mahadevan, C. Li, G. Biswas, Identification of critical inspection sam- ples among railroad wheels by similarity-based agglomerative clustering. Integrated Comput. Aided Eng. 18, 203–219 (2011).73. G. Pettet, S. Nannapaneni, B. Stadnick, A. Dubey, G. Biswas, “Incident analysis and prediction using clustering and bayesian network” in 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Com- puting & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) (IEEE, 2017), pp. 1–8.