Spectral Networks and Locally Connected Networks on Graphs

Convolutional Neural Networks are extremely efficient architectures in image and audio recognition tasks, thanks to their ability to exploit the local translational invariance of signal classes over their domain. In this paper we consider possible generalizations of CNNs to signals defined on more general domains without the action of a translation group. In particular, we propose two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian. We show through experiments that for low-dimensional graphs it is possible to learn convolutional layers with a number of parameters independent of the input size, resulting in efficient deep architectures.

[1]  Fan Chung,et al.  Spectral Graph Theory , 1996 .

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  Peter Schröder,et al.  Multiresolution signal processing for meshes , 1999, SIGGRAPH.

[4]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[5]  Mark Crovella,et al.  Graph wavelets for spatial traffic analysis , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[6]  R. Coifman,et al.  Diffusion Wavelets , 2004 .

[7]  Achi Brandt,et al.  Fast multiscale clustering and manifold identification , 2006, Pattern Recognit..

[8]  Inderjit S. Dhillon,et al.  Weighted Graph Cuts without Eigenvectors A Multilevel Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Nicolas Le Roux,et al.  Learning the 2-D Topology of Images , 2007, NIPS.

[10]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[11]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[12]  Quoc V. Le,et al.  Tiled convolutional neural networks , 2010, NIPS.

[13]  Ronald R. Coifman,et al.  Multiscale Wavelets on Trees, Graphs and High Dimensional Data: Theory and Applications to Semi Supervised Learning , 2010, ICML.

[14]  Yann LeCun,et al.  Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields , 2010, ArXiv.

[15]  Yann LeCun,et al.  Convolutional Learning of Spatio-temporal Features , 2010, ECCV.

[16]  Achi Brandt,et al.  Efficient Multilevel Eigensolvers with Applications to Data Analysis Tasks , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Andrew Y. Ng,et al.  Selecting Receptive Fields in Deep Networks , 2011, NIPS.

[18]  Quoc V. Le,et al.  Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis , 2011, CVPR 2011.

[19]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

[20]  Trevor Darrell,et al.  Beyond spatial pyramids: Receptive field learning for pooled image features , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Yann LeCun,et al.  Convolutional neural networks applied to house numbers digit classification , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  Leonidas J. Guibas,et al.  Wavelets on Graphs via Deep Learning , 2013, NIPS.