ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

TL;DR

ACE-HGNN introduces an adaptive hyperbolic GNN that learns optimal curvature for better hierarchical graph representation, outperforming fixed-curvature models across various datasets.

Contribution

It proposes a novel reinforcement learning framework with two agents to adaptively learn the best hyperbolic curvature for graph neural networks.

Findings

Significant performance improvements over fixed-curvature HGNNs.

Effective adaptation to diverse hierarchical structures in real-world graphs.

Good generalization across multiple datasets.

Abstract

Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks. Most existingGNNs embed graph data into Euclidean space and thus are less effective to capture the ubiquitous hierarchical structures in real-world networks. Hyperbolic Graph Neural Networks(HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning. In hyperbolic geometry, the graph hierarchical structure can be reflected by the curvatures of the hyperbolic space, and different curvatures can model different hierarchical structures of a graph. However, most existing HGNNs manually set the curvature to a fixed value for simplicity, which achieves a suboptimal performance of graph learning due to the complex and diverse hierarchical structures of the graphs. To resolve this problem, we propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Specifically, ACE-HGNN exploits a multi-agent reinforcement learning framework and contains two agents, ACE-Agent andHGNN-Agent for learning the curvature and node representations, respectively. The two agents are updated by a NashQ-leaning algorithm collaboratively, seeking the optimal hyperbolic space indexed by the curvature. Extensive experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.