Unit Ball Model for Hierarchical Embeddings in Complex Hyperbolic Space

Learning the representation of data with hierarchical structures in the hyperbolic space attracts increasing attention in recent years. Due to the constant negative curvature, the hyperbolic space resembles tree metrics and captures the tree-like properties of hierarchical graphs naturally, which enables the hyperbolic embeddings to improve over traditional Euclidean models. However, most graph data, even the data with hierarchical structures are not trees and they usually do not ubiquitously match the constant curvature property of the hyperbolic space. To address this limitation of hyperbolic embeddings, we explore the complex hyperbolic space, which has the variable negative curvature, for representation learning. Specifically, we propose to learn the graph embeddings in the unit ball model of the complex hyperbolic space. The unit ball model based embeddings have a more powerful representation capacity to capture a variety of hierarchical graph structures. Through experiments on synthetic and real-world data, we show that our approach improves over the hyperbolic embedding models significantly.