Abstract
An increasing number of applications require processing of signals defined on weighted graphs. While wavelets provide a flexible tool for signal processing in the classical setting of regular domains, the existing graph wavelet constructions are less flexible—they are guided solely by the structure of the underlying graph and do not take directly into consideration the particular class of signals to be processed. This chapter introduces a machine learning framework for constructing graph wavelets that can sparsely represent a given class of signals. Our construction uses the lifting scheme, and is based on the observation that the recurrent nature of the lifting scheme gives rise to a structure resembling a deep auto-encoder network. Particular properties that the resulting wavelets must satisfy determine the training objective and the structure of the involved neural networks. The training is unsupervised, and is conducted similarly to the greedy pre-training of a stack of auto-encoders. After training is completed, we obtain a linear wavelet transform that can be applied to any graph signal in time and memory linear in the size of the graph. Improved sparsity of our wavelet transform for the test signals is confirmed via experiments both on synthetic and real data.
This work was done at Computer science department, Stanford University.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Mark Schmidt, http://www.di.ens.fr/~mschmidt/Software/minFunc.html.
- 2.
National Climatic Data Center, http://www.ftp://ftp.ncdc.noaa.gov/pub/data/gsod/2012/.
References
D.I. Shuman, S.K. Narang, P. Frossard, A. Ortega, P. Vandergheynst, 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)
M. Crovella, E.D. Kolaczyk, Graph wavelets for spatial traffic analysis, in INFOCOM (2003)
A.D. Szlam, M. Maggioni, R.R. Coifman, J.C. Bremer, Diffusion-driven multiscale analysis on manifolds and graphs: top-down and bottom-up constructions, in SPIE (2005), p. 5914
M. Gavish, B. Nadler, R.R. Coifman, Multiscale wavelets on trees, graphs and high dimensional data: theory and applications to semi supervised learning, in ICML (2010), pp. 367–374
R.R. Coifman, M. Maggioni, Diffusion wavelets. Appl. Comput. Harmon. Anal. 21(1), 53–94 (2006). https://doi.org/10.1016/j.acha.2006.04.004
D.K. Hammond, P. Vandergheynst, R. Gribonval, Wavelets on graphs via spectral graph theory. Appl. Comput. Harmon. Anal. 30(2), 129–150 (2011). https://doi.org/10.1016/j.acha.2010.04.005
I. Ram, M. Elad, I. Cohen, Generalized tree-based wavelet transform. IEEE Trans. Signal Process. 59(9), 4199–4209 (2011)
R.M. Rustamov, Average interpolating wavelets on point clouds and graphs. CoRR (2011). arXiv:1110.2227
S.K. Narang, A. Ortega, Multi-dimensional separable critically sampled wavelet filterbanks on arbitrary graphs, in ICASSP (2012), pp. 3501–3504
M.N. Do, Y.M. Lu, Multidimensional filter banks and multiscale geometric representations. Found. Trends Signal Process. 5(3), 157–264 (2012)
G.E. Hinton, S. Osindero, Y.W. Teh, A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006). https://doi.org/10.1162/neco.2006.18.7.1527
G.E. Hinton, R. Salakhutdinov, Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006). https://doi.org/10.1126/science.1127647
Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, Greedy layer-wise training of deep networks, in Adv. Neural Inf. Process. Syst. 19, ed. by B. Schölkopf, J. Platt, T. Hoffman (MIT Press, MA, 2007), pp. 153–160
M. Ranzato, C. Poultney, S. Chopra, Y. LeCun, Efficient learning of sparse representations with an energy-based model, in Adv. Neural Inf. Process. Syst. 19, ed. by B. Schölkopf, J. Platt, T. Hoffman (MIT Press, MA, 2007), pp. 1137–1144
R. Rustamov, L.J. Guibas, Wavelets on graphs via deep learning, in Advances in Neural Information Processing Systems 26, ed. by C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, K.Q. Weinberger (Curran Associates, Inc., 2013), pp. 998–1006. http://papers.nips.cc/paper/5046-wavelets-on-graphs-via-deep-learning.pdf
F. Scarselli, M. Gori, A.C. Tsoi, M. Hagenbuchner, G. Monfardini, The graph neural network model. Trans. Neural Netw. 20(1), 61–80 (2009). https://doi.org/10.1109/TNN.2008.2005605
M.M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, P. Vandergheynst, Geometric deep learning: going beyond euclidean data. IEEE Signal Process. Mag. 34(4), 18–42 (2017). https://doi.org/10.1109/MSP.2017.2693418
S. Mallat, A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way, 3rd edn. (Academic Press, 2008)
W. Sweldens, The lifting scheme: a construction of second generation wavelets. SIAM J. Math. Anal. 29(2), 511–546 (1998)
I. Daubechies, W. Sweldens, Factoring wavelet transforms into lifting steps. J. Fourier Anal. Appl. 4(3), 245–267 (1998)
R.L. Claypoole, G. Davis, W. Sweldens, R.G. Baraniuk, Nonlinear wavelet transforms for image coding via lifting. IEEE Trans. Image Process. 12(12), 1449–1459 (2003)
D.P. Kingma, J. Ba, Adam: A method for stochastic optimization (2015)
M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mané, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viégas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, X. Zheng, TensorFlow: Large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. Software available from tensorflow.org
M. Belkin, P. Niyogi, Semi-supervised learning on riemannian manifolds. Mach. Learn. 56(1–3), 209–239 (2004)
A.Y. Ng, M.I. Jordan, Y. Weiss, On spectral clustering: analysis and an algorithm, in NIPS (2001), pp. 849–856
R.R. Coifman, S. Lafon, Diffusion maps. Applied and Computational Harmonic Analysis 21(1), 5–30 (2006). https://doi.org/10.1016/j.acha.2006.04.006
X. Zhu, Z. Ghahramani, J.D. Lafferty, Semi-supervised learning using gaussian fields and harmonic functions, in ICML (2003), pp. 912–919
A. Georghiades, P. Belhumeur, D. Kriegman, From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 643–660 (2001)
X. Zhang, X. Dong, P. Frossard, Learning of structured graph dictionaries, in ICASSP (2012), pp. 3373–3376. https://doi.org/10.1109/ICASSP.2012.6288639
J. Bruna, S. Mallat, Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872–1886 (2013)
Acknowledgements
We thank Jonathan Huang for discussions and especially for his advice regarding the experimental section. The authors acknowledge the support of NSF grants FODAVA 808515 and DMS 1228304, AFOSR grant FA9550-12-1-0372, ONR grant N00014-13-1-0341, a Google research award, and the Max Plack Center for Visual Computing and Communications.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Rustamov, R.M., Guibas, L.J. (2019). Wavelets on Graphs via Deep Learning. In: Stanković, L., Sejdić, E. (eds) Vertex-Frequency Analysis of Graph Signals. Signals and Communication Technology. Springer, Cham. https://doi.org/10.1007/978-3-030-03574-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-03574-7_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03573-0
Online ISBN: 978-3-030-03574-7
eBook Packages: EngineeringEngineering (R0)