Symbolic Regression on Network Properties

  • Marcus MärtensEmail author
  • Fernando Kuipers
  • Piet Van Mieghem
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10196)


Networks are continuously growing in complexity, which creates challenges for determining their most important characteristics. While analytical bounds are often too conservative, the computational effort of algorithmic approaches does not scale well with network size. This work uses Cartesian Genetic Programming for symbolic regression to evolve mathematical equations that relate network properties directly to the eigenvalues of network adjacency and Laplacian matrices. In particular, we show that these eigenvalues are powerful features to evolve approximate equations for the network diameter and the isoperimetric number, which are hard to compute algorithmically. Our experiments indicate a good performance of the evolved equations for several real-world networks and we demonstrate how the generalization power can be influenced by the selection of training networks and feature sets.


Symbolic regression Complex networks Cartesian Genetic Programming 


  1. 1.
    Page, L., Brin, S., Motwani, R., Winograd, T.: The PageRank citation ranking: bringing order to the web. Technical report, Stanford University, Stanford, CA (1998)Google Scholar
  2. 2.
    Van Mieghem, P.: Graph eigenvectors, fundamental weights and centrality metrics for nodes in networks. arXiv preprint arXiv:1401.4580 (2014)
  3. 3.
    Schmidt, M., Lipson, H.: Distilling free-form natural laws from experimental data. Science 324(5923), 81–85 (2009)CrossRefGoogle Scholar
  4. 4.
    Strogatz, S.H.: Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry, and Engineering. Studies in Nonlinearity. Westview Press, Boulder (2014)zbMATHGoogle Scholar
  5. 5.
    Schmidt, M., Lipson, H.: Solving iterated functions using genetic programming. In: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers, pp. 2149–2154. ACM (2009)Google Scholar
  6. 6.
    Menezes, T., Roth, C.: Symbolic regression of generative network models. Sci. Rep. 4 (2014). Article No. 6284, doi: 10.1038/srep06284
  7. 7.
    McConaghy, T.: FFX: fast, scalable, deterministic symbolic regression technology. In: Riolo, R., Vladislavleva, E., Moore, J.H. (eds.) Genetic Programming Theory and Practice IX, pp. 235–260. Springer, New York (2011)CrossRefGoogle Scholar
  8. 8.
    Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection, vol. 1. MIT press, Cambridge (1992)zbMATHGoogle Scholar
  9. 9.
    McConaghy, T., Eeckelaert, T., Gielen, G.: CAFFEINE: template-free symbolic model generation of analog circuits via canonical form functions and genetic programming. In: Proceedings of the Conference on Design, Automation and Test in Europe, vol. 2, pp. 1082–1087. IEEE Computer Society (2005)Google Scholar
  10. 10.
    Augusto, D.A., Barbosa, H.J.: Symbolic regression via genetic programming. In: 6th Brazilian Symposium on Neural Networks, pp. 173–178. IEEE (2000)Google Scholar
  11. 11.
    Miller, J.F.: Cartesian Genetic Programming. Springer, Heidelberg (2011)CrossRefzbMATHGoogle Scholar
  12. 12.
    Harding, S., Miller, J.F.: Evolution of robot controller using cartesian genetic programming. In: Keijzer, M., Tettamanzi, A., Collet, P., Hemert, J., Tomassini, M. (eds.) EuroGP 2005. LNCS, vol. 3447, pp. 62–73. Springer, Heidelberg (2005). doi: 10.1007/978-3-540-31989-4_6 CrossRefGoogle Scholar
  13. 13.
    Khan, M.M., Khan, G.M.: A novel neuroevolutionary algorithm: cartesian genetic programming evolved artificial neural network (CGPANN). In: Proceedings of the 8th International Conference on Frontiers of Information Technology, p. 48. ACM (2010)Google Scholar
  14. 14.
    Harding, S., Graziano, V., Leitner, J., Schmidhuber, J.: MT-CGP: mixed type cartesian genetic programming. In: Proceedings of the 14th Annual Conference on Genetic and Evolutionary Computation, pp. 751–758. ACM (2012)Google Scholar
  15. 15.
    Miller, J.F.: Evolution of digital filters using a gate array model. In: Poli, R., Voigt, H.-M., Cagnoni, S., Corne, D., Smith, G.D., Fogarty, T.C. (eds.) EvoWorkshops 1999. LNCS, vol. 1596, pp. 17–30. Springer, Heidelberg (1999). doi: 10.1007/10704703_2 CrossRefGoogle Scholar
  16. 16.
    Vasicek, Z., Sekanina, L.: Evolutionary approach to approximate digital circuits design. IEEE Trans. Evol. Comput. 19(3), 432–444 (2015)CrossRefGoogle Scholar
  17. 17.
    Vasicek, Z.: Cartesian GP in optimization of combinational circuits with hundreds of inputs and thousands of gates. In: Machado, P., Heywood, M.I., McDermott, J., Castelli, M., García-Sánchez, P., Burelli, P., Risi, S., Sim, K. (eds.) EuroGP 2015. LNCS, vol. 9025, pp. 139–150. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-16501-1_12 Google Scholar
  18. 18.
    Miller, J.F., Smith, S.L.: Redundancy and computational efficiency in cartesian genetic programming. IEEE Trans. Evol. Comput. 10(2), 167–174 (2006)CrossRefGoogle Scholar
  19. 19.
    Turner, A.J., Miller, J.F.: Cartesian genetic programming: why no bloat? In: Nicolau, M., Krawiec, K., Heywood, M.I., Castelli, M., García-Sánchez, P., Merelo, J.J., Rivas Santos, V.M., Sim, K. (eds.) EuroGP 2014. LNCS, vol. 8599, pp. 222–233. Springer, Heidelberg (2014). doi: 10.1007/978-3-662-44303-3_19 Google Scholar
  20. 20.
    Van Mieghem, P.: Graph Spectra for Complex Networks. Cambridge University Press, Cambridge (2011)zbMATHGoogle Scholar
  21. 21.
    Van Mieghem, P., Omic, J., Kooij, R.: Virus spread in networks. IEEE/ACM Trans. Netw. 17(1), 1–14 (2009)CrossRefGoogle Scholar
  22. 22.
    Fiedler, M.: Algebraic connectivity of graphs. Czechoslovak Math. J. 23(2), 298–305 (1973)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Alon, N., Milman, V.D.: \(\lambda \)1, isoperimetric inequalities for graphs, and superconcentrators. J. Comb. Theory Ser. B 38(1), 73–88 (1985)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Mohar, B.: Eigenvalues, diameter, and mean distance in graphs. Graphs Comb. 7(1), 53–64 (1991)MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Chung, F.R., Faber, V., Manteuffel, T.A.: An upper bound on the diameter of a graph from eigenvalues associated with its Laplacian. SIAM J. Discret. Math. 7(3), 443–457 (1994)MathSciNetCrossRefzbMATHGoogle Scholar
  26. 26.
    Van Dam, E.R., Haemers, W.H.: Eigenvalues and the diameter of graphs. Linear Multilinear Algebra 39(1–2), 33–44 (1995)MathSciNetzbMATHGoogle Scholar
  27. 27.
    Mohar, B.: Isoperimetric numbers of graphs. J. Comb. Theory Ser. B 47(3), 274–291 (1989)MathSciNetCrossRefzbMATHGoogle Scholar
  28. 28.
    Bollobás, B.: Random Graphs. Springer, New York (1998)CrossRefzbMATHGoogle Scholar
  29. 29.
    Goldman, B.W., Punch, W.F.: Analysis of cartesian genetic programming’s evolutionary mechanisms. IEEE Trans. Evol. Comput. 19(3), 359–373 (2015)CrossRefGoogle Scholar
  30. 30.
    Rossi, R.A., Ahmed, N.K.: An interactive data repository with visual analytics. SIGKDD Explor. 17(2), 37–41 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Marcus Märtens
    • 1
    Email author
  • Fernando Kuipers
    • 1
  • Piet Van Mieghem
    • 1
  1. 1.Faculty of Electrical Engineering, Mathematics and Computer ScienceDelft University of TechnologyDelftThe Netherlands

Personalised recommendations