Curvature Graph Network

Graph-structured data is prevalent in many domains. Despite the widely celebrated success of deep neural networks, their power in graph-structured data is yet to be fully explored. We propose a novel network architecture that incorporates advanced graph structural features. In particular, we leverage discrete graph curvature, which measures how the neighborhoods of a pair of nodes are structurally related. The curvature of an edge (x, y) defines the distance taken to travel from neighbors of x to neighbors of y, compared with the length of edge (x, y). It is a much more descriptive feature compared to previously used features that only focus on node specific attributes or limited topological information such as degree. Our curvature graph convolution network outperforms state-of-the-art on various synthetic and real-world graphs, especially the larger and denser ones.

[1]  Kathryn B. Laskey,et al.  Stochastic blockmodels: First steps , 1983 .

[2]  S. Yau,et al.  Ricci curvature of graphs , 2011 .

[3]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.

[4]  Cristopher Moore,et al.  Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[5]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[6]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

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

[8]  Alessandro Sperduti,et al.  Supervised neural networks for the classification of structures , 1997, IEEE Trans. Neural Networks.

[9]  Karl-Theodor Sturm,et al.  On the geometry of metric measure spaces. II , 2006 .

[10]  C. Villani,et al.  Ricci curvature for metric-measure spaces via optimal transport , 2004, math/0412127.

[11]  Anton van den Hengel,et al.  Image-Based Recommendations on Styles and Substitutes , 2015, SIGIR.

[12]  Karl-Theodor Sturm,et al.  Mass transportation and rough curvature bounds for discrete spaces , 2009 .

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

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

[15]  Y. Ollivier.  Ricci curvature of Markov chains on metric spaces , 2007, math/0701886.

[16]  Robin Forman,et al.  Bochner's Method for Cell Complexes and Combinatorial Ricci Curvature , 2003, Discret. Comput. Geom..

[17]  Martin Grohe,et al.  Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks , 2018, AAAI.

[18]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[19]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[20]  Emil Saucan,et al.  Forman-Ricci Flow for Change Detection in Large Dynamic Data Sets , 2016, Axioms.

[21]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[22]  Jie Gao,et al.  Ricci curvature of the Internet topology , 2015, 2015 IEEE Conference on Computer Communications (INFOCOM).

[23]  Jason Altschuler,et al.  Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration , 2017, NIPS.

[24]  Emil Saucan,et al.  Characterizing complex networks with Forman-Ricci curvature and associated geometric flows , 2016, J. Complex Networks.

[25]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[26]  M. Newman,et al.  Renormalization Group Analysis of the Small-World Network Model , 1999, cond-mat/9903357.

[27]  Jonathan Masci,et al.  Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Jon M. Kleinberg,et al.  Navigation in a small world , 2000, Nature.

[29]  Jie Gao,et al.  Network Alignment by Discrete Ollivier-Ricci Flow , 2018, GD.

[30]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[31]  Stephan Günnemann,et al.  Pitfalls of Graph Neural Network Evaluation , 2018, ArXiv.

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

[33]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[34]  Alessandro Sperduti,et al.  A general framework for adaptive processing of data structures , 1998, IEEE Trans. Neural Networks.