Metapath-based Hyperbolic Contrastive Learning for Heterogeneous Graph Embedding

--In heterogeneous graphs, a metapath can be defined as a sequence of node or link types, allowing the learning of both semantic information and structural properties. From a structural perspective, various hierarchical or power-law structures, each corresponding to a specific metapath, can be observed in real-world heterogeneous graphs. Recent studies in heterogeneous graph embedding use hyperbolic space to capture such complex structures. The hyperbolic space, characterized by a constant negative curvature and exponentially expanding space, aligns well with the structural properties of heterogeneous graphs. However, although heterogeneous graphs inherently possess diverse power-law structures, most hyperbolic heterogeneous graph embedding models rely on a single hyperbolic space. This approach may fail to effectively capture the diverse power-law structures within heterogeneous graphs. T o address this limitation, we propose a M etapath-based H yperbolic C ontrastive L earning framework (MHCL), which uses multiple hyperbolic spaces to capture diverse complex structures within heterogeneous graphs. Specifically, by learning each hyperbolic space to describe the distribution of complex structures corresponding to each metapath, it is possible to capture semantic information effectively. Since metapath embeddings represent distinct semantic information, preserving their discriminability is important when aggregating them to obtain node representations. Therefore, we use a contrastive learning approach to optimize MHCL and improve the discriminability of metapath embed-dings. We conduct comprehensive experiments to evaluate the effectiveness of MHCL. The experimental results demonstrate that MHCL outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.