Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks

  • Sofia Ira KtenaEmail author
  • Sarah Parisot
  • Enzo Ferrante
  • Martin Rajchl
  • Matthew Lee
  • Ben Glocker
  • Daniel Rueckert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10433)


Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects or interactions between elements. The choice of a distance or similarity metric is, however, not trivial and can be highly dependent on the application at hand. In this work, we propose a novel metric learning method to evaluate distance between graphs that leverages the power of convolutional neural networks, while exploiting concepts from spectral graph theory to allow these operations on irregular graphs. We demonstrate the potential of our method in the field of connectomics, where neuronal pathways or functional connections between brain regions are commonly modelled as graphs. In this problem, the definition of an appropriate graph similarity function is critical to unveil patterns of disruptions associated with certain brain disorders. Experimental results on the ABIDE dataset show that our method can learn a graph similarity metric tailored for a clinical application, improving the performance of a simple k-nn classifier by 11.9% compared to a traditional distance metric.


  1. 1.
    Abraham, A., Milham, M., Di Martino, A., Craddock, R.C., Samaras, D., Thirion, B., Varoquaux, G.: Deriving reproducible biomarkers from multi-site resting-state data: an autism-based example. NeuroImage 147, 736–745 (2016)CrossRefGoogle Scholar
  2. 2.
    Craddock, C., Sikka, S., Cheung, B., Khanuja, R., Ghosh, S., et al.: Towards automated analysis of connectomes: the configurable pipeline for the analysis of connectomes (C-PAC). Front Neuroinf. 42 (2013)Google Scholar
  3. 3.
    Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: NIPS, pp. 3837–3845 (2016)Google Scholar
  4. 4.
    Desikan, R.S., Ségonne, F., Fischl, B., Quinn, B.T., Dickerson, B.C., et al.: An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. NeuroImage 31(3), 968–980 (2006)CrossRefGoogle Scholar
  5. 5.
    Di Martino, A., Yan, C.G., Li, Q., Denio, E., Castellanos, F.X., et al.: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol. Psychiatry 19(6), 659–667 (2014)CrossRefGoogle Scholar
  6. 6.
    Hammond, D.K., Vandergheynst, P., Gribonval, R.: Wavelets on graphs via spectral graph theory. Appl. Comput. Harmonic Anal. 30(2), 129–150 (2011)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint (2016). arXiv:1609.02907
  8. 8.
    Kumar, B., Carneiro, G., Reid, I., et al.: Learning local image descriptors with deep siamese and triplet convolutional networks by minimising global loss functions. In: IEEE CVPR, pp. 5385–5394 (2016)Google Scholar
  9. 9.
    Livi, L., Rizzi, A.: The graph matching problem. Pattern Anal. Appl. 16(3), 253–283 (2013)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Monti, F., Boscaini, D., Masci, J., Rodolà, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. arXiv preprint (2016). arXiv:1611.08402
  11. 11.
    Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: ICML (2016)Google Scholar
  12. 12.
    Raj, A., Mueller, S.G., Young, K., Laxer, K.D., Weiner, M.: Network-level analysis of cortical thickness of the epileptic brain. NeuroImage 52(4), 1302–1313 (2010)CrossRefGoogle Scholar
  13. 13.
    Shervashidze, N., Vishwanathan, S., Petri, T., Mehlhorn, K., Borgwardt, K.M.: Efficient graphlet kernels for large graph comparison. AISTATS 5, 488–495 (2009)Google Scholar
  14. 14.
    Shuman, D.I., Narang, S.K., Frossard, P., Ortega, A., Vandergheynst, P.: The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Process. Mag. 30(3), 83–98 (2013)CrossRefGoogle Scholar
  15. 15.
    Takerkart, S., Auzias, G., Thirion, B., Ralaivola, L.: Graph-based inter-subject pattern analysis of fMRI data. PloS one 9(8), e104586 (2014)CrossRefGoogle Scholar
  16. 16.
    Zagoruyko, S., Komodakis, N.: Learning to compare image patches via convolutional neural networks. In: IEEE CVPR, pp. 4353–4361 (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Sofia Ira Ktena
    • 1
    Email author
  • Sarah Parisot
    • 1
  • Enzo Ferrante
    • 1
  • Martin Rajchl
    • 1
  • Matthew Lee
    • 1
  • Ben Glocker
    • 1
  • Daniel Rueckert
    • 1
  1. 1.Biomedical Image Analysis GroupImperial College LondonLondonUK

Personalised recommendations