Rotated Lorentzian Graph Embedding Model for Asymmetric Proximity

18 Jan 2023 | 3.00pm (Singapore Time)

Graph embedding, which aims to learn low-dimensional node representations to preserve original graph structures, has attracted extensive research interests. However, most existing graph embedding models represent nodes in Euclidean spaces, which cannot effectively preserve complex patterns, e.g., hierarchical structures. While recent hyperbolic embedding models have been proposed to preserve the hierarchical information in negative curvature spaces, the existing hyperbolic models fail to model the asymmetric proximity between nodes. To address this challenge, Dr Feng Shanshan and his team investigate a new asymmetric hyperbolic network representation problem that targets at preserving the hierarchical structures and asymmetric proximity for general directed graphs. 

In this talk, Dr Feng will introduce a novel Rotated Lorentzian Embedding (ROLE) model, which yields two main benefits. First, their model could effectively capture both implicit and explicit hierarchical structures that come from the network topology and category information of nodes, respectively. Second, it could model the asymmetric proximity using rotation transformations. Dr Feng will also share empirical results to demonstrate that the proposed approach would consistently outperform various state-of-the-art graph representation models.