Skip to main content
SpringerLink
Log in

Dynamic graph summarization: a tensor decomposition approach

  • Published:
Data Mining and Knowledge Discovery Aims and scope Submit manuscript

Abstract

Due to the scale and complexity of todays’ social networks, it becomes infeasible to mine them with traditional approaches. A possible solution to reduce such scale and complexity is to produce a compact (lossy) version of the network that represents its major properties. This task is known as graph summarization, which is the subject of this research. Our focus is on time-evolving graphs, a more complex scenario where the dynamics of the network also should be taken into account. We address this problem using tensor decomposition, which enables us to capture the multi-way structure of the time-evolving network. This property is unique and is impossible to obtain with other approaches such as matrix factorization. Experimental evaluation on five real world networks implies promising results demonstrating that tensor decomposition is quite useful for summarizing dynamic networks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  • Abbe E (2017) Community detection and stochastic block models: recent developments. arXiv preprint arXiv:1703.10146

  • Aharony N, Pan W, Ip C, Khayal I, Pentland A (2011) Social fMRI: investigating and shaping social mechanisms in the real world. Pervasive Mob Comput 7(6):643–659

    Article  Google Scholar 

  • Aicher C, Jacobs AZ, Clauset A (2014) Learning latent block structure in weighted networks. J Complex Netw 3(2):221–248

    Article  MathSciNet  Google Scholar 

  • Bader BW, Kolda TG (2007) Efficient MATLAB computations with sparse and factored tensors. SIAM J Sci Comput 30(1):205–231

    Article  MathSciNet  MATH  Google Scholar 

  • Bader BW, Kolda TG et al (2015) Matlab tensor toolbox version 2.6. http://www.sandia.gov/~tgkolda/TensorToolbox/. Accessed 15 Sept 2016

  • Bebendorf M, Rjasanow S (2003) Adaptive low-rank approximation of collocation matrices. Computing 70(1):1–24

    Article  MathSciNet  MATH  Google Scholar 

  • Brandes U, Lerner J (2010) Structural similarity: spectral methods for relaxed blockmodeling. J Classif 27(3):279–306

    Article  MathSciNet  MATH  Google Scholar 

  • Breiger RL, Pattison PE (1978) The joint role structure of two communities’ elites. Sociol Methods Res 7(2):213–226

    Article  Google Scholar 

  • Bro R, Kiers HA (2003) A new efficient method for determining the number of components in parafac models. J Chemom 17(5):274–286

    Article  Google Scholar 

  • Buehrer G, Chellapilla K (2008) A scalable pattern mining approach to web graph compression with communities. In: Proceedings of the 2008 international conference on web search and data mining. ACM, pp 95–106

  • Desmier E, Plantevit M, Robardet C, Boulicaut JF (2012) Cohesive co-evolution patterns in dynamic attributed graphs. In: Ganascia JG, Lenca P, Petit JM (eds) Discovery science. DS 2012. Lecture notes in computer science, vol 7569. Springer, Berlin, Heidelberg, pp 110–124

  • Doreian P, Batagelj V, Ferligoj A (2005) Generalized blockmodeling, vol 25. Cambridge University Press, Cambridge

    MATH  Google Scholar 

  • Fortunato S (2010) Community detection in graphs. Phys Rep 486(3–5):75–174

    Article  MathSciNet  Google Scholar 

  • Gansner ER, Koren Y, North SC (2005) Topological fisheye views for visualizing large graphs. IEEE Trans Vis Comput Graph 11(4):457–468

    Article  Google Scholar 

  • Henderson K, Gallagher B, Eliassi-Rad T, Tong H, Basu S, Akoglu L, Koutra D, Faloutsos C, Li L (2012) Rolx: structural role extraction and mining in large graphs. In: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 1231–1239

  • Isella L, Stehl J, Barrat A, Cattuto C, Pinton JF, den Broeck WV (2011) What’s in a crowd? analysis of face-to-face behavioral networks. J Theor Biol 271(1):166–180. http://www.sociopatterns.org/datasets/infectious-sociopatterns-dynamic-contact-networks/

  • Kodinariya TM, Makwana PR (2013) Review on determining number of cluster in k-means clustering. Int J 1(6):90–95

    Google Scholar 

  • Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Rev 51(3):455–500

    Article  MathSciNet  MATH  Google Scholar 

  • Kolda T, Sun J (2008) Scalable tensor decompositions for multi-aspect data mining. In: The eighth IEEE international conference on data mining. IEEE, pp 363–372

  • LeFevre K, Terzi E (2010) Grass: graph structure summarization. In: Proceedings of the 2010 SIAM international conference on data mining. SIAM, pp 454–465

  • Leskovec J, Kleinberg J, Faloutsos C (2005) Graphs over time: densification laws, shrinking diameters and possible explanations. In: Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining. ACM, pp 177–187

  • Li CT, Lin SD (2009) Egocentric information abstraction for heterogeneous social networks. In: International conference on advances in social network analysis and mining, 2009, ASONAM’09. IEEE, pp 255–260

  • Liu Y, Dighe A, Safavi T, Koutra D (2016) A graph summarization: a survey. arXiv preprint arXiv:1612.04883

  • Mathioudakis M, Bonchi F, Castillo C, Gionis A, Ukkonen A (2011) Sparsification of influence networks. In: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 529–537

  • Mitchell TM (1997) Machine learning, 1st edn. McGraw-Hill Inc, New York

    MATH  Google Scholar 

  • Navlakha S, Rastogi R, Shrivastava N (2008) Graph summarization with bounded error. In: Proceedings of the 2008 ACM SIGMOD international conference on management of data. ACM, pp 419–432

  • Papalexakis EE (2016) Automatic unsupervised tensor mining with quality assessment. In: Proceedings of the 2016 SIAM international conference on data mining. SIAM, pp 711–719

  • Piperno A (2008) Search space contraction in canonical labeling of graphs. arXiv preprint arXiv:0804.4881

  • Priebe CE, Conroy JM, Marchette DJ, Park Y (2005) Scan statistics on enron graphs. Comput Math Organ Theory 11(3):229–247

    Article  MATH  Google Scholar 

  • Ralaivola L, Swamidass SJ, Saigo H, Baldi P (2005) Graph kernels for chemical informatics. Neural Netw 18(8):1093–1110

    Article  Google Scholar 

  • Riondato M, García-Soriano D, Bonchi F (2017) Graph summarization with quality guarantees. Data Min Knowl Discov 31(2):314–349

    Article  MathSciNet  Google Scholar 

  • Rossi RA, Ahmed NK (2015a) The network data repository with interactive graph analytics and visualization. In: Proceedings of the twenty-ninth AAAI conference on artificial intelligence. http://networkrepository.com. Accessed 27 Feb 2017

  • Rossi RA, Ahmed NK (2015b) Role discovery in networks. IEEE Trans Knowl Data Eng 27(4):1112–1131

    Article  Google Scholar 

  • Shah N, Koutra D, Zou T, Gallagher B, Faloutsos C (2015) Timecrunch: interpretable dynamic graph summarization. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1055–1064

  • Shen Z, Ma KL, Eliassi-Rad T (2006) Visual analysis of large heterogeneous social networks by semantic and structural abstraction. IEEE Trans Vis Comput Graph 12(6):1427–1439

    Article  Google Scholar 

  • Spielman DA, Teng SH (2011) Spectral sparsification of graphs. SIAM J Comput 40(4):981–1025

    Article  MathSciNet  MATH  Google Scholar 

  • Tsalouchidou I, Morales GDF, Bonchi F, Baeza-Yates R (2016) Scalable dynamic graph summarization. In: 2016 IEEE international conference on big data (big data). IEEE, pp 1032–1039

Download references

Acknowledgements

This work is financed by the ERDF - European Regional Development Fund through the Operational Programme for Competitiveness and Internationalisation - COMPETE 2020 Programme within project POCI-01-0145-FEDER-006961, and by National Funds through the FCT - Fundação para a Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) as part of project UID/EEA/50014/2013. Sofia Fernandes also acknowledges the support of FCT via the PhD scholarship PD/BD/114189/2016. The authors would also like to acknowledge the SocioPatterns collaboration for making the Infectious Patterns dataset available.

Author information

Authors and Affiliations

  1. LIAAD, INESC TEC, University of Porto, Porto, Portugal

    Sofia Fernandes & João Gama

  2. Department of Biostatistics, University of Oslo, Oslo, Norway

    Hadi Fanaee-T

Authors
  1. Sofia Fernandes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hadi Fanaee-T
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. João Gama
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sofia Fernandes.

Additional information

Responsible editors: Jesse Davis, Elisa Fromont, Derek Greene, Björn Bringmann.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

The results of the signed Wilcoxon rank tests are shown in Table 7. We did not apply the tests on Friends&Family and DBLP datasets, when using a window length of 6, because the number of available windows was extremely small (3 and 4, respectively).

Table 7 p Values of the signed Wilcoxon rank tests involving tenClustS, with respect to: reconstruction error (top table), compression cost (middle table) and running time (bottom table)
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fernandes, S., Fanaee-T, H. & Gama, J. Dynamic graph summarization: a tensor decomposition approach. Data Min Knowl Disc 32, 1397–1420 (2018). https://doi.org/10.1007/s10618-018-0583-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10618-018-0583-9

Keywords

Search

Navigation