Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE

While Hyperbolic Graph Neural Network (HGNN) has recently emerged as a powerful tool dealing with hierarchical graph data, the limitations of scalability and efficiency hinder itself from generalizing to deep models. In this paper, by envisioning depth as a continuous-time embedding evolution, we decouple the HGNN and reframe the information propagation as a partial differential equation, letting node-wise attention undertake the role of diffusivity within the Hyperbolic Neural PDE (HPDE). By introducing theoretical principles \textit{e.g.,} field and flow, gradient, divergence, and diffusivity on a non-Euclidean manifold for HPDE integration, we discuss both implicit and explicit discretization schemes to formulate numerical HPDE solvers. Further, we propose the Hyperbolic Graph Diffusion Equation (HGDE) -- a flexible vector flow function that can be integrated to obtain expressive hyperbolic node embeddings. By analyzing potential energy decay of embeddings, we demonstrate that HGDE is capable of modeling both low- and high-order proximity with the benefit of local-global diffusivity functions. Experiments on node classification and link prediction and image-text classification tasks verify the superiority of the proposed method, which consistently outperforms various competitive models by a significant margin.

[1]  Jiaxu Liu,et al.  DeepHGCN: Recipe for Efficient and Scalable Deep Hyperbolic Graph Convolutional Networks , 2023, 2310.02027.

[2]  Junchi Yan,et al.  DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion , 2023, ICLR.

[3]  Wee Peng Tay,et al.  On the Robustness of Graph Neural Diffusion to Topology Perturbations , 2022, NeurIPS.

[4]  Heng Huang,et al.  Improving Social Network Embedding via New Second-Order Continuous Graph Neural Networks , 2022, KDD.

[5]  Nurendra Choudhary,et al.  Towards Scalable Hyperbolic Neural Networks using Taylor Series Approximations , 2022, ArXiv.

[6]  Chris De Sa,et al.  Random Laplacian Features for Learning with Hyperbolic Space , 2022, ICLR.

[7]  T. Konstantin Rusch,et al.  Graph-Coupled Oscillator Networks , 2022, ICML.

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

[9]  Davide Eynard,et al.  Beltrami Flow and Neural Diffusion on Graphs , 2021, NeurIPS.

[10]  Xia Hu,et al.  Dirichlet Energy Constrained Learning for Deep Graph Neural Networks , 2021, NeurIPS.

[11]  Michael M. Bronstein,et al.  GRAND: Graph Neural Diffusion , 2021, ICML.

[12]  Peng Li,et al.  Fully Hyperbolic Neural Networks , 2021, ACL.

[13]  Chuan Shi,et al.  Lorentzian Graph Convolutional Networks , 2021, WWW.

[14]  Jie Yin,et al.  Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective , 2021, ICLR.

[15]  Yaliang Li,et al.  Simple and Deep Graph Convolutional Networks , 2020, ICML.

[16]  L. Akoglu,et al.  Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs , 2020, NeurIPS.

[17]  Jonathan T. Barron,et al.  Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains , 2020, NeurIPS.

[18]  Chao Chen,et al.  Curvature Graph Network , 2020, ICLR.

[19]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[20]  Kevin Chen-Chuan Chang,et al.  Geom-GCN: Geometric Graph Convolutional Networks , 2020, ICLR.

[21]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[22]  Atsushi Yamashita,et al.  Graph Neural Ordinary Differential Equations , 2019, ArXiv.

[23]  Octavian-Eugen Ganea,et al.  Constant Curvature Graph Convolutional Networks , 2019, ICML.

[24]  Jaewoo Kang,et al.  Graph Transformer Networks , 2019, NeurIPS.

[25]  Jure Leskovec,et al.  Hyperbolic Graph Convolutional Neural Networks , 2019, NeurIPS.

[26]  Bin Luo,et al.  Semi-Supervised Learning With Graph Learning-Convolutional Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Bernard Ghanem,et al.  DeepGCNs: Can GCNs Go As Deep As CNNs? , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Kilian Q. Weinberger,et al.  Simplifying Graph Convolutional Networks , 2019, ICML.

[29]  Charline Le Lan,et al.  Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders , 2019, NeurIPS.

[30]  Jure Leskovec,et al.  Evolution of resilience in protein interactomes across the tree of life , 2018, Proceedings of the National Academy of Sciences.

[31]  Stephan Günnemann,et al.  Predict then Propagate: Graph Neural Networks meet Personalized PageRank , 2018, ICLR.

[32]  Gary Bécigneul,et al.  Riemannian Adaptive Optimization Methods , 2018, ICLR.

[33]  David Duvenaud,et al.  Neural Ordinary Differential Equations , 2018, NeurIPS.

[34]  Thomas Hofmann,et al.  Hyperbolic Neural Networks , 2018, NeurIPS.

[35]  Thomas Hofmann,et al.  Hyperbolic Entailment Cones for Learning Hierarchical Embeddings , 2018, ICML.

[36]  Dahua Lin,et al.  Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition , 2018, AAAI.

[37]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[38]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[40]  Douwe Kiela,et al.  Poincaré Embeddings for Learning Hierarchical Representations , 2017, NIPS.

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

[42]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[44]  M. Hamann On the tree-likeness of hyperbolic spaces , 2011, Mathematical Proceedings of the Cambridge Philosophical Society.

[45]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[46]  Amin Vahdat,et al.  Hyperbolic Geometry of Complex Networks , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[47]  Abraham Albert Ungar,et al.  A Gyrovector Space Approach to Hyperbolic Geometry , 2009, A Gyrovector Space Approach to Hyperbolic Geometry.

[48]  M. Newman,et al.  Hierarchical structure and the prediction of missing links in networks , 2008, Nature.

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

[50]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

[51]  E. Beltrami Teoria fondamentale degli spazii di curvatura costante , 1868 .

[52]  Ernst Hairer,et al.  Solving Differential Equations on Manifolds , 2011 .

[53]  A. Ungar,et al.  Analytic Hyperbolic Geometry: Mathematical Foundations And Applications , 2005 .