Graph Neural Aggregation-diffusion with Metastability

• URL: http://arxiv.org/abs/2403.20221v1
• Date: Fri, 29 Mar 2024 15:05:57 GMT
• Title: Graph Neural Aggregation-diffusion with Metastability
• Authors: Kaiyuan Cui, Xinyan Wang, Zicheng Zhang, Weichen Zhao,
• Abstract summary: Continuous graph neural models based on differential equations have expanded the architecture of graph neural networks (GNNs) We propose GRADE inspired by graph aggregation-diffusion equations, which includes the delicate balance between nonlinear diffusion and aggregation induced by interaction potentials. We prove that GRADE achieves competitive performance across various benchmarks and alleviates the over-smoothing issue in GNNs.
• Score: 4.040326569845733
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continuous graph neural models based on differential equations have expanded the architecture of graph neural networks (GNNs). Due to the connection between graph diffusion and message passing, diffusion-based models have been widely studied. However, diffusion naturally drives the system towards an equilibrium state, leading to issues like over-smoothing. To this end, we propose GRADE inspired by graph aggregation-diffusion equations, which includes the delicate balance between nonlinear diffusion and aggregation induced by interaction potentials. The node representations obtained through aggregation-diffusion equations exhibit metastability, indicating that features can aggregate into multiple clusters. In addition, the dynamics within these clusters can persist for long time periods, offering the potential to alleviate over-smoothing effects. This nonlinear diffusion in our model generalizes existing diffusion-based models and establishes a connection with classical GNNs. We prove that GRADE achieves competitive performance across various benchmarks and alleviates the over-smoothing issue in GNNs evidenced by the enhanced Dirichlet energy.

Related papers

• Neural Message Passing Induced by Energy-Constrained Diffusion [79.9193447649011]
  We propose an energy-constrained diffusion model as a principled interpretable framework for understanding the mechanism of MPNNs. We show that the new model can yield promising performance for cases where the data structures are observed (as a graph), partially observed or completely unobserved.
  arXiv  Detail & Related papers  (2024-09-13T17:54:41Z)
• Advancing Graph Generation through Beta Diffusion [49.49740940068255]
  Graph Beta Diffusion (GBD) is a generative model specifically designed to handle the diverse nature of graph data. We propose a modulation technique that enhances the realism of generated graphs by stabilizing critical graph topology.
  arXiv  Detail & Related papers  (2024-06-13T17:42:57Z)
• Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE [36.48610732998552]
  We introduce theoretical principles textite.g., field and flow, gradient, divergence, and diffusivity on a non-Euclidean manifold for HPDE integration. We propose the Hyperbolic Graph Diffusion Equation (HGDE) -- a flexible vector flow function that can be integrated to obtain expressive hyperbolic node embeddings.
  arXiv  Detail & Related papers  (2024-06-03T12:50:58Z)
• A charge-preserving method for solving graph neural diffusion networks [0.0]
  This paper gives a systematic mathematical interpretation of the diffusion problem on which Graph Neural Networks (GNNs) models are based. Knowing the charge values and their conservation along the evolution flow could provide a way to understand how GNNs and other networks work with their learning capabilities.
  arXiv  Detail & Related papers  (2023-12-16T01:06:31Z)
• Advective Diffusion Transformers for Topological Generalization in Graph Learning [69.2894350228753]
  We show how graph diffusion equations extrapolate and generalize in the presence of varying graph topologies. We propose a novel graph encoder backbone, Advective Diffusion Transformer (ADiT), inspired by advective graph diffusion equations.
  arXiv  Detail & Related papers  (2023-10-10T08:40:47Z)
• SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases [66.61789780666727]
  We show how the second-order continuity can be incorporated into GNNs while maintaining the equivariant property. We also offer theoretical insights into SEGNO, highlighting that it can learn a unique trajectory between adjacent states. Our model yields a significant improvement over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-08-25T07:15:58Z)
• Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting [60.03169701753824]
  We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting. The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
  arXiv  Detail & Related papers  (2023-05-16T11:38:19Z)
• On the Robustness of Graph Neural Diffusion to Topology Perturbations [30.284359808863588]
  We show that graph neural PDEs are intrinsically more robust against topology perturbation as compared to other GNNs. We propose a general graph neural PDE framework based on which a new class of robust GNNs can be defined.
  arXiv  Detail & Related papers  (2022-09-16T07:19:35Z)
• Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs [16.88394293874848]
  We use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs. By considering a hierarchy of increasingly general sheaves, we study how the ability of the sheaf diffusion process to achieve linear separation of the classes in the infinite time limit expands. We prove that when the sheaf is non-trivial, discretised parametric diffusion processes have greater control than GNNs over their behaviour.
  arXiv  Detail & Related papers  (2022-02-09T17:25:02Z)
• Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
  We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
  arXiv  Detail & Related papers  (2022-02-05T08:21:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.