Learning Convolutional Neural Networks for Graphs

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.

[1]  Karsten M. Borgwardt,et al.  The graphlet spectrum , 2009, ICML '09.

[2]  Luc De Raedt,et al.  Graph Invariant Kernels , 2015, IJCAI.

[3]  Brendan D. McKay,et al.  Practical graph isomorphism, II , 2013, J. Symb. Comput..

[4]  Jure Leskovec,et al.  Community Structure in Large Networks: Natural Cluster Sizes and the Absence of Large Well-Defined Clusters , 2008, Internet Math..

[5]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[6]  Thomas Gärtner,et al.  On Graph Kernels: Hardness Results and Efficient Alternatives , 2003, COLT.

[7]  Takunari Miyazaki,et al.  The complexity of McKay's canonical labeling algorithm , 1995, Groups and Computation.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[10]  Pinar Yanardag,et al.  Deep Graph Kernels , 2015, KDD.

[11]  John D. Lafferty,et al.  Diffusion Kernels on Graphs and Other Discrete Input Spaces , 2002, ICML.

[12]  S. Shen-Orr,et al.  Network motifs: simple building blocks of complex networks. , 2002, Science.

[13]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[14]  A. Debnath,et al.  Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. , 1991, Journal of medicinal chemistry.

[15]  S. V. N. Vishwanathan,et al.  Graph kernels , 2007 .

[16]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[17]  Karsten M. Borgwardt,et al.  The skew spectrum of graphs , 2008, ICML '08.

[18]  David Haussler,et al.  Convolution kernels on discrete structures , 1999 .

[19]  P. Dobson,et al.  Distinguishing enzyme structures from non-enzymes without alignments. , 2003, Journal of molecular biology.

[20]  Ashwin Srinivasan,et al.  Statistical Evaluation of the Predictive Toxicology Challenge 2000-2001 , 2003, Bioinform..

[21]  M. Newman,et al.  The structure of scientific collaboration networks. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[23]  D. Hubel,et al.  Receptive fields and functional architecture of monkey striate cortex , 1968, The Journal of physiology.

[24]  George Karypis,et al.  Comparison of descriptor spaces for chemical compound retrieval and classification , 2006, Sixth International Conference on Data Mining (ICDM'06).

[25]  Hans-Peter Kriegel,et al.  Shortest-path kernels on graphs , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[26]  S. Shen-Orr,et al.  Networks Network Motifs : Simple Building Blocks of Complex , 2002 .

[27]  Izhar Wallach,et al.  AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery , 2015, ArXiv.

[28]  David Haussler,et al.  Unsupervised learning of distributions on binary vectors using two layer networks , 1991, NIPS 1991.

[29]  Kristian Kersting,et al.  Counting Belief Propagation , 2009, UAI.

[30]  Kurt Mehlhorn,et al.  Weisfeiler-Lehman Graph Kernels , 2011, J. Mach. Learn. Res..

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

[32]  Eugene M. Luks,et al.  Isomorphism of graphs of bounded valence can be tested in polynomial time , 1980, 21st Annual Symposium on Foundations of Computer Science (sfcs 1980).

[33]  Kurt Mehlhorn,et al.  Efficient graphlet kernels for large graph comparison , 2009, AISTATS.

[34]  Robert J. Marks,et al.  An artificial neural network for spatiotemporal: application to phoneme classification , 1987 .

[35]  U. Alon.  Network motifs: theory and experimental approaches , 2007, Nature Reviews Genetics.

[36]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[37]  Robert J. Marks,et al.  An Artificial Neural Network for Spatio-Temporal Bipolar Patterns: Application to Phoneme Classification , 1987, NIPS.

[38]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[39]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[40]  Hannu Toivonen,et al.  Statistical evaluation of the predictive toxicology challenge , 2000 .

[41]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[42]  B. Douglas.  The Weisfeiler-Lehman Method and Graph Isomorphism Testing , 2011, 1101.5211.

[43]  Paul Erdös,et al.  Random Graph Isomorphism , 1980, SIAM J. Comput..

[44]  Paul S. Bonsma,et al.  Tight Lower and Upper Bounds for the Complexity of Canonical Colour Refinement , 2013, Theory of Computing Systems.

[45]  Roman Garnett,et al.  Power Iterated Color Refinement , 2014, AAAI.