Symplectic Structure-Aware Hamiltonian (Graph) Embeddings

by   Jiaxu Liu, et al.

In traditional Graph Neural Networks (GNNs), the assumption of a fixed embedding manifold often limits their adaptability to diverse graph geometries. Recently, Hamiltonian system-inspired GNNs are proposed to address the dynamic nature of such embeddings by incorporating physical laws into node feature updates. In this work, we present SAH-GNN, a novel approach that generalizes Hamiltonian dynamics for more flexible node feature updates. Unlike existing Hamiltonian-inspired GNNs, SAH-GNN employs Riemannian optimization on the symplectic Stiefel manifold to adaptively learn the underlying symplectic structure during training, circumventing the limitations of existing Hamiltonian GNNs that rely on a pre-defined form of standard symplectic structure. This innovation allows SAH-GNN to automatically adapt to various graph datasets without extensive hyperparameter tuning. Moreover, it conserves energy during training such that the implicit Hamiltonian system is physically meaningful. To this end, we empirically validate SAH-GNN's superior performance and adaptability in node classification tasks across multiple types of graph datasets.


page 1

page 2

page 3

page 4


Hierarchical Model Selection for Graph Neural Netoworks

Node classification on graph data is a major problem, and various graph ...

Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs

Graph Neural Networks (GNNs) are emerging machine learning models on gra...

Bayesian Graph Neural Networks with Adaptive Connection Sampling

We propose a unified framework for adaptive connection sampling in graph...

Dynamic Labeling for Unlabeled Graph Neural Networks

Existing graph neural networks (GNNs) largely rely on node embeddings, w...

Reversible and irreversible bracket-based dynamics for deep graph neural networks

Recent works have shown that physics-inspired architectures allow the tr...

Boosting Heterogeneous Catalyst Discovery by Structurally Constrained Deep Learning Models

The discovery of new catalysts is one of the significant topics of compu...

SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention

With the frequent happening of privacy leakage and the enactment of priv...

Please sign up or login with your details

Forgot password? Click here to reset