ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

• Published in: 2021 IEEE International Conference on Data Mining (ICDM) pp. 111 - 120
• Main Authors: Fu, Xingcheng, Li, Jianxin, Wu, Jia, Sun, Qingyun, Ji, Cheng, Wang, Senzhang, Tan, Jiajun, Peng, Hao, Yu, Philip S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2021
• Subjects: Adaptation models; Adaptive systems; Conferences; Geometry; Graph neural networks; graph representation learning; hyperbolic graph neural network; hyperbolic space; Reinforcement learning; Representation learning
• ISSN: 2374-8486
• DOI: 10.1109/ICDM51629.2021.00021

Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks. Most existing GNNs 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 Neural Network 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 and HGNN-Agent for learning the curvature and node representations, respectively. The two agents are updated by a Nash Q-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.