Embedding Node Structural Role Identity into Hyperbolic Space
This work addresses the need for better structural role embeddings in networks, but it is incremental as it adapts an existing method to a new space.
The paper tackled the problem of embedding node structural roles into hyperbolic space, extending struct2vec to a hyperboloid model, and found that hyperbolic space is more effective than Euclidean space for this task on real-world and synthetic networks.
Recently, there has been an interest in embedding networks in hyperbolic space, since hyperbolic space has been shown to work well in capturing graph/network structure as it can naturally reflect some properties of complex networks. However, the work on network embedding in hyperbolic space has been focused on microscopic node embedding. In this work, we are the first to present a framework to embed the structural roles of nodes into hyperbolic space. Our framework extends struct2vec, a well-known structural role preserving embedding method, by moving it to a hyperboloid model. We evaluated our method on four real-world and one synthetic network. Our results show that hyperbolic space is more effective than euclidean space in learning latent representations for the structural role of nodes.