Advertisement

Genetic Programming and Evolvable Machines

, Volume 20, Issue 3, pp 385–411 | Cite as

GP-based methods for domain adaptation: using brain decoding across subjects as a test-case

  • Roberto SantanaEmail author
  • Luis Marti
  • Mengjie Zhang
Article

Abstract

Research on classifier transferability intends that the information gathered in the solution of a given classification problem could be reused in the solution of similar or related problems. We propose the evolution of transferable classifiers based on the use of multi-objective genetic programming and new fitness-functions that evaluate the amount of transferability. We focus on the domain adaptation scenario in which the problem to be solved is the same in the source and target domains, but the distribution of data is different between domains. As a real-world test case we address the brain decoding problem, whose goal is to predict the stimulus presented to a subject from the analysis of his brain activity. Brain decoding across subjects attempts to reuse the classifiers learned from some subjects in the classification of the others. We evolved GP-based classifiers using different variants of the introduced approach to test their effectiveness on data obtained from a brain decoding experiment involving 16 subjects. Our results show that the GP-based classifiers evolved trying to maximize transferability are able to improve classification accuracy over other classical classifiers that incorporate domain adaptation methods. Moreover, after comparing our algorithm to importance-weighted cross validation (in conjunction with many ML methods), we conclude that our approach achieves state of the art results in terms of transferability.

Keywords

Genetic programming Domain adaptation Brain signal analysis 

Notes

Acknowledgements

R. Santana acknowledges support by the Basque Government (ELKARTEK programs), and Spanish Ministry of Economy and Competitiveness MINECO (project TIN2016-78365-R). This work started thanks to a Thelxinoe Grant granted to R. Santana in the context of EMA2/S2 THELXINOE: Erasmus Euro-Oceanian project, 545783-EM-1-2013-ES-ERA MUNDUS-EMA22.

Supplementary material

10710_2019_9352_MOESM1_ESM.pdf (237 kb)
Supplementary material 1 (pdf 236 KB)

References

  1. 1.
    I.M. Alvarez, W.N. Browne, M. Zhang, Reusing learned functionality in XCS: code fragments with constructed functionality and constructed features, in Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary Computation (ACM, 2014), pp. 969–976Google Scholar
  2. 2.
    I. Arnaldo, U.-M. O’Reilly, K. Veeramachaneni, Building predictive models via feature synthesis, in Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation (ACM, 2015), pp. 983–990Google Scholar
  3. 3.
    U. Bhowan, M. Johnston, M. Zhang, X. Yao, Evolving diverse ensembles using genetic programming for classification with unbalanced data. IEEE Trans. Evolut. Comput. 17(3), 368–386 (2013)CrossRefGoogle Scholar
  4. 4.
    U. Bhowan, M. Johnston, M. Zhang, X. Yao, Reusing genetic programming for ensemble selection in classification of unbalanced data. IEEE Trans. Evolut. Comput. 18(6), 893–908 (2014)CrossRefGoogle Scholar
  5. 5.
    S. Bickel, M. Brückner, T. Scheffer, Discriminative learning for differing training and test distributions, in Proceedings of the 24th International Conference on Machine learning (ACM, 2007), pp. 81–88Google Scholar
  6. 6.
    J. Blitzer, R. McDonald, F. Pereira, Domain adaptation with structural correspondence learning, in Proceedings of the 2006 conference on empirical methods in natural language processing (Association for Computational Linguistics, 2006), pp. 120–128Google Scholar
  7. 7.
    L. Breiman, Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  8. 8.
    Q. Chen, B. Xue, M. Zhang, Generalisation and domain adaptation in GP with gradient descent for symbolic regression, in Proceedings of the IEEE Congress on Evolutionary Computation CEC-2015 (IEEE, 2015), pp. 1137–1144Google Scholar
  9. 9.
    S. Dalhoumi, G. Derosiere, G. Dray, J. Montmain, S. Perrey, Graph-based transfer learning for managing brain signals variability in NIRS-based BCIs, in Information Processing and Management of Uncertainty in Knowledge-Based Systems (Springer, 2014), pp. 294–303Google Scholar
  10. 10.
    K. Deb, A. Pratap, S. Agarwal, T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)CrossRefGoogle Scholar
  11. 11.
    T.T.H. Dinh, T.H. Chu, Q.U. Nguyen, Transfer learning in genetic programming, in Proceedings of the IEEE Congress on Evolutionary Computation CEC-2015, Sendai, Japan (IEEE Press, 2015), pp. 1145–1151Google Scholar
  12. 12.
    P.G. Espejo, S. Ventura, F. Herrera, A survey on the application of genetic programming to classification. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 40(2), 121–144 (2010)CrossRefGoogle Scholar
  13. 13.
    L. Feng, Y. Ong, M. Lim, I. Tsang, Memetic search with inter-domain learning: a realization between CVRP and CARP. IEEE Trans. Evol. Comput. 19(5), 644–658 (2014)CrossRefGoogle Scholar
  14. 14.
    P. Geurts, D. Ernst, L. Wehenkel, Extremely randomized trees. Mach. Learn. 63(1), 3–42 (2006)CrossRefzbMATHGoogle Scholar
  15. 15.
    M.W. Hauschild, M. Pelikan, K. Sastry, D.E. Goldberg, Using previous models to bias structural learning in the hierarchical BOA. Evol. Comput. 20(1), 135–160 (2012)CrossRefGoogle Scholar
  16. 16.
    J.D. Haynes, G. Reeves, Decoding mental states from brain activity in humans. Nat. Revi. Neurosci. 7, 523–534 (2006)CrossRefGoogle Scholar
  17. 17.
    R.N. Henson, D.G. Wakeman, V. Litvak, K.J. Friston, A parametric empirical Bayesian framework for the EEG/MEG inverse problem: generative models for multi-subject and multi-modal integration. Front. Hum. Neurosci. (2011).  https://doi.org/10.3389/fnhum.2011.00076 Google Scholar
  18. 18.
    H. Huttunen, T. Manninen, J.-P. Kauppi, J. Tohka, Mind reading with regularized multinomial logistic regression. Mach. Vis. Appl. 24(6), 1311–1325 (2013)CrossRefGoogle Scholar
  19. 19.
    V. Ingalalli, S. Silva, M. Castelli, L. Vanneschi, A multi-dimensional genetic programming approach for multi-class classification problems, in European Conference on Genetic Programming (Springer, 2014), pp. 48–60Google Scholar
  20. 20.
    M. Iqbal, W. Browne, M. Zhang, Reusing building blocks of extracted knowledge to solve complex, large-scale Boolean problems. IEEE Trans. Evol. Comput. 18(4), 465–480 (2014)CrossRefGoogle Scholar
  21. 21.
    M. Iqbal, B. Xue, M. Zhang, Reusing extracted knowledge in genetic programming to solve complex texture image classification problems, in Proceedings of the 20th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining. Part II, vol. 9652 (Springer, New York, 2016), pp. 117–129Google Scholar
  22. 22.
    M. Iqbal, M. Zhang, B. Xue, Improving classification on images by extracting and transferring knowledge in genetic programming, in Proceedings of the IEEE Congress on Evolutionary Computation CEC-2016 (IEEE, 2016), pp. 3582–3589Google Scholar
  23. 23.
    W. Jaskowski, K. Krawiec, B. Wieloch, Knowledge reuse in genetic programming applied to visual learning, in Proceedings of the 9th annual conference on Genetic and evolutionary computation (ACM, 2007), pp. 1790–1797Google Scholar
  24. 24.
    H. Kang, Y. Nam, S. Choi, Composite common spatial pattern for subject-to-subject transfer. IEEE Signal Process. Lett. 16(8), 683–686 (2009)CrossRefGoogle Scholar
  25. 25.
    K.N. Kay, T. Naselaris, R.J. Prenger, J.L. Gallant, Identifying natural images from human brain activity. Nature 452(7185), 352–355 (2008)CrossRefGoogle Scholar
  26. 26.
    W. La Cava, J.H. Moore, Ensemble representation learning: an analysis of fitness and survival for wrapper-based genetic programming methods, in Proceedings of the Genetic and Evolutionary Computation Conference (ACM, 2017), pp. 961–968Google Scholar
  27. 27.
    W. La Cava, S. Silva, K. Danai, L. Spector, L. Vanneschi, J.H. Moore, Multidimensional genetic programming for multiclass classification. Swarm Evol. Comput. 44, 260–272 (2019)CrossRefGoogle Scholar
  28. 28.
    M. Lebedev, M. Nicolelis, Brain-machine interfaces: past, present and future. TRENDS Neurosci. 29(9), 536–546 (2006)CrossRefGoogle Scholar
  29. 29.
    X. Li, W. He, K. Hirasawa, Learning and evolution of genetic network programming with knowledge transfer, in Proceedings of the IEEE Congress on Evolutionary Computation CEC-2014 (IEEE, 2014), pp. 798–805Google Scholar
  30. 30.
    M. Loog, Nearest neighbor-based importance weighting, in IEEE International Work Learning for Signal Processing (IEEE, 2012), pp. 1–6Google Scholar
  31. 31.
    F. Lotte, C. Guan, Learning from other subjects helps reducing brain computer interface calibration time, in Proceedings of the IEEE 35th International Conference on Acoustics, Speech, and Signal Processing (IEEE, 2010), pp. 614–617Google Scholar
  32. 32.
    J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, G. Zhang, Transfer learning using computational intelligence: a survey. Knowl. Based Syst. 80, 14–23 (2015)CrossRefGoogle Scholar
  33. 33.
    E. Olivetti, S.M. Kia, P. Avesani, MEG decoding across subjects, in Proceedings of the 2014 International Workshop on Pattern Recognition in Neuroimaging (2014), pp. 1–4Google Scholar
  34. 34.
    D. O’Neill, H. Al-Sahaf, B. Xue, M. Zhang, Common subtrees in related problems: A novel transfer learning approach for genetic programming, in Proceedings of the IEEE Congress on Evolutionary Computation CEC-2017, San Sebastian, Spain (IEEE, 2017), pp. 1287–1294Google Scholar
  35. 35.
    S. Pan, Q. Yang, A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  36. 36.
    F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar
  37. 37.
    H. Peng, F. Long, C. Ding, Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal. Mach. Intell. 27(8), 1226–1238 (2005)CrossRefGoogle Scholar
  38. 38.
    H. Ramoser, J. Muller-Gerking, G. Pfurtscheller, Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehabilit. Eng. 8(4), 441–446 (2000)CrossRefGoogle Scholar
  39. 39.
    W. Samek, F.C. Meinecke, K.R. Müller, Transferring subspaces between subjects in brain-computer interfacing. IEEE Trans. Biomed. Eng. 60(8), 2289–2298 (2013)CrossRefGoogle Scholar
  40. 40.
    R. Santana, A. Mendiburu, J. A. Lozano, Structural transfer using EDAs: an application to multi-marker tagging SNP selection, in Proceedings of the 2012 Congress on Evolutionary Computation CEC-2012, Brisbane, Australia. (IEEE Press, 2012), pp. 3484–3491 (Best Paper Award of 2012 Congress on Evolutionary Computation)Google Scholar
  41. 41.
    S. Satpal, S. Sarawagi, Domain adaptation of conditional probability models via feature subsetting, in Proceeding of the Knowledge Discovery in Databases Conference. PKDD-2007 (Springer, 2007), pp. 224–235Google Scholar
  42. 42.
    H. Shimodaira, Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plan. Inference 90(2), 227–244 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  43. 43.
    S. Silva, L. Muñoz, L. Trujillo, V. Ingalalli, M. Castelli, L. Vanneschi, Multiclass classification through multidimensional clustering, in Genetic Programming Theory and Practice XIII, ed. by R. Riolo, W. P. Worzel, M. Kotanchek, A. Kordon (Springer, Berlin, 2016), pp. 219–239CrossRefGoogle Scholar
  44. 44.
    M. Sugiyama, M. Krauledat, K.-R. Müller, Covariate shift adaptation by importance weighted cross validation. J. Mach. Learn. Res. 8(May), 985–1005 (2007)zbMATHGoogle Scholar
  45. 45.
    V. Vapnik, The Nature of Statistical Learning Theory (Springer, New York, 2000)CrossRefzbMATHGoogle Scholar
  46. 46.
    H. Wang, L. Jiao, X. Yao, An improved two-archive algorithm for many-objective optimization. IEEE Trans. Evol. Comput. 19(4), 524–541 (2015)CrossRefGoogle Scholar
  47. 47.
    J. Wolpaw, N. Birbaumer, D. McFarland, G. Pfurtscheller, T. Vaughan, Brain-computer interfaces for communication and control. Clin. Neurophysiol. 113(6), 767–791 (2002)CrossRefGoogle Scholar
  48. 48.
    D. Xing, W. Dai, G. Xue, Y. Yu, Bridged refinement for transfer learning, in Proceeding of the Knowledge Discovery in Databases Conference. PKDD-2007 (Springer, 2007), pp. 324–335Google Scholar
  49. 49.
    M. Yamada, T. Suzuki, T. Kanamori, H. Hachiya, M. Sugiyama, Relative density-ratio estimation for robust distribution comparison. Neural Comput. 25(5), 1324–1370 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  50. 50.
    H.-F. Yu, F.-L. Huang, C.-J. Lin, Dual coordinate descent methods for logistic regression and maximum entropy models. Mach. Learn. 85(1–2), 41–75 (2011)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.University of the Basque Country (UPV/EHU)San SebastiánSpain
  2. 2.Inria ChileLas CondesChile
  3. 3.School of Engineering and Computer ScienceVictoria University of WellingtonWellingtonNew Zealand

Personalised recommendations