Curvature Filtrations for Graph Generative Model Evaluation

Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in an efficient manner. Curvature constitutes one such property of graphs, and has recently started to prove useful in characterising graphs. Its expressive properties, stability, and practical utility in model evaluation remain largely unexplored, however. We combine graph curvature descriptors with cutting-edge methods from topological data analysis to obtain robust, expressive descriptors for evaluating graph generative models.

[1]  M. Bronstein,et al.  Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Sreenivas Gollapudi,et al.  Affinity-Aware Graph Networks , 2022, ArXiv.

[3]  Fuhai Li,et al.  How Powerful are K-hop Message Passing Graph Neural Networks , 2022, NeurIPS.

[4]  Roger Wattenhofer,et al.  A Theoretical Comparison of Graph Neural Network Extensions , 2022, ICML.

[5]  R. Lambiotte,et al.  Discrete curvature on graphs from the effective resistance , 2022, 2201.06385.

[6]  Francesco Di Giovanni,et al.  Understanding over-squashing and bottlenecks on graphs via curvature , 2021, ICLR.

[7]  T. Jaakkola,et al.  Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design , 2021, ICLR.

[8]  Debarghya Ghoshdastidar,et al.  Graphon based Clustering and Testing of Networks: Algorithms and Theory , 2021, ICLR.

[9]  Karsten M. Borgwardt,et al.  Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions , 2021, ICLR.

[10]  Karsten M. Borgwardt,et al.  Topological Graph Neural Networks , 2021, ICLR.

[11]  Weiwei Jiang,et al.  Graph Neural Network for Traffic Forecasting: A Survey , 2021, Expert Syst. Appl..

[12]  Quinn Perian,et al.  On the Wasserstein Distance Between $k$-Step Probability Measures on Finite Graphs , 2021, 2110.10363.

[13]  Supanat Kamtue,et al.  Transportation Distance between Probability Measures on the Infinite Regular Tree , 2021, 2107.09876.

[14]  Oriol Vinyals,et al.  Highly accurate protein structure prediction with AlphaFold , 2021, Nature.

[15]  Floris Geerts,et al.  Graph Neural Networks with Local Graph Parameters , 2021, NeurIPS.

[16]  Quoc V. Le,et al.  A graph placement methodology for fast chip design , 2021, Nature.

[17]  Alexis Arnaudon,et al.  Unfolding the multiscale structure of networks with dynamical Ollivier-Ricci curvature , 2021, Nature Communications.

[18]  Floris Geerts,et al.  Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework , 2020, ICML.

[19]  Karsten M. Borgwardt,et al.  Graph Kernels: State-of-the-Art and Future Challenges , 2020, Found. Trends Mach. Learn..

[20]  C. Trugenberger,et al.  Ollivier Curvature of Random Geometric Graphs Converges to Ricci Curvature of Their Riemannian Manifolds , 2020, Discrete & Computational Geometry.

[21]  Jure Leskovec,et al.  Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning , 2020, NeurIPS.

[22]  Kristian Kersting,et al.  TUDataset: A collection of benchmark datasets for learning with graphs , 2020, ArXiv.

[23]  Bo Dai,et al.  Scalable Deep Generative Modeling for Sparse Graphs , 2020, ICML.

[24]  J. Leskovec,et al.  Identification of disease treatment mechanisms through the multiscale interactome , 2020, Nature Communications.

[25]  J. Jost,et al.  A simple differential geometry for complex networks , 2020, Network Science.

[26]  Stefano Ermon,et al.  Permutation Invariant Graph Generation via Score-Based Generative Modeling , 2020, AISTATS.

[27]  Joan Bruna,et al.  Can graph neural networks count substructures? , 2020, NeurIPS.

[28]  Marc Niethammer,et al.  Graph Filtration Learning , 2019, ICML.

[29]  Renjie Liao,et al.  Efficient Graph Generation with Graph Recurrent Attention Networks , 2019, NeurIPS.

[30]  Jiawei Zhou,et al.  A Hierarchy of Graph Neural Networks Based on Learnable Local Features , 2019, ArXiv.

[31]  Karsten M. Borgwardt,et al.  Wasserstein Weisfeiler-Lehman Graph Kernels , 2019, NeurIPS.

[32]  Ruosong Wang,et al.  Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels , 2019, NeurIPS.

[33]  Yizhou Sun,et al.  Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification , 2019, ArXiv.

[34]  Davide Eynard,et al.  Fake News Detection on Social Media using Geometric Deep Learning , 2019, ArXiv.

[35]  Oleg Verbitsky,et al.  On Weisfeiler-Leman Invariance: Subgraph Counts and Related Graph Properties , 2018, FCT.

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

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

[38]  W. Shiu,et al.  The effect on eigenvalues of connected graphs by adding edges , 2018, Linear Algebra and its Applications.

[39]  Shiping Liu,et al.  Bakry–Émery curvature and diameter bounds on graphs , 2018, Calculus of Variations and Partial Differential Equations.

[40]  Jure Leskovec,et al.  GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models , 2018, ICML.

[41]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[42]  Jiao Gu,et al.  Comparative analysis of two discretizations of Ricci curvature for complex networks , 2017, Scientific Reports.

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

[44]  Florentin Münch,et al.  Bakry–Émery curvature and diameter bounds on graphs , 2016, 1608.07778.

[45]  Søren Hauberg,et al.  Geodesic exponential kernels: When curvature and linearity conflict , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Peter Bubenik,et al.  Statistical topological data analysis using persistence landscapes , 2012, J. Mach. Learn. Res..

[47]  Shiping Liu,et al.  Ollivier’s Ricci Curvature, Local Clustering and Curvature-Dimension Inequalities on Graphs , 2011, Discret. Comput. Geom..

[48]  Jacobus H. Koolen,et al.  On electric resistances for distance-regular graphs , 2011, Eur. J. Comb..

[49]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[50]  G. V. Paolini,et al.  Quantifying the chemical beauty of drugs. , 2012, Nature chemistry.

[51]  Jennifer Neville,et al.  Tied Kronecker product graph models to capture variance in network populations , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[52]  Y. Ollivier.  Ricci curvature of metric spaces , 2007 .

[53]  David Cohen-Steiner,et al.  Stability of Persistence Diagrams , 2005, Discret. Comput. Geom..

[54]  Brian K. Shoichet,et al.  ZINC - A Free Database of Commercially Available Compounds for Virtual Screening , 2005, J. Chem. Inf. Model..

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

[56]  David Haussler,et al.  Convolution Kernels on Discrete Structures UCSC CRL , 1999 .

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

[58]  R. Zamar,et al.  A multivariate Kolmogorov-Smirnov test of goodness of fit , 1997 .

[59]  Norman L. Biggs,et al.  Potential Theory on Distance-Regular Graphs , 1993, Combinatorics, Probability and Computing.

[60]  L. Asz.  Random Walks on Graphs: a Survey , 2022 .