TY - JOUR
T1 - ROLE: Rotated Lorentzian Graph Embedding Model for Asymmetric Proximity
AU - Feng, Shanshan
AU - Chen, Lisi
AU - Zhao, Kaiqi
AU - Wei, Wei
AU - Song, Xuemeng
AU - Shang, Shuo
AU - Kalnis, Panos
AU - Shao, Ling
N1 - KAUST Repository Item: Exported on 2022-12-08
Acknowledgements: This work was supported in part by the National Natural Science Foundation of China under Grant No. 62276110, U2001212, U21B2046, 62032001, and 61932004. Besides, it was also supported in part by CCF-AFSG Research Fund under Grant No.RF20210005, and in part by the fund of Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL). We thank the anonymous reviewers for their insightful comments.
PY - 2022/11/14
Y1 - 2022/11/14
N2 - 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. Very recently, several hyperbolic embedding models have been proposed to preserve the hierarchical information in negative curvature spaces. Nevertheless, existing hyperbolic models fail to model the asymmetric proximity between nodes. To address this, we investigate a new asymmetric hyperbolic network representation problem, which targets at jointly preserving the hierarchical structures and asymmetric proximity for general directed graphs. We solve this problem by proposing a novel Rotated Lorentzian Embedding (ROLE) model, which yields two main benefits. First, our model can effectively capture both implicit and explicit hierarchical structures that come from the network topology and category information of nodes, respectively. Second, it can model the asymmetric proximity using rotation transformations. Specifically, we represent each node with a Lorentzian embedding vector, and learn two rotation matrices to reflect the direction of edges. We conduct extensive experiments on four real-world directed graph datasets. Empirical results demonstrate that the proposed approach consistently outperforms various state-of-the-art embedding models. In particular, ROLE achieves HR@1 scores up to 19.8% higher and NDCG@5 scores up to 11.3% higher than the best baselines on the task of node recommendation
AB - 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. Very recently, several hyperbolic embedding models have been proposed to preserve the hierarchical information in negative curvature spaces. Nevertheless, existing hyperbolic models fail to model the asymmetric proximity between nodes. To address this, we investigate a new asymmetric hyperbolic network representation problem, which targets at jointly preserving the hierarchical structures and asymmetric proximity for general directed graphs. We solve this problem by proposing a novel Rotated Lorentzian Embedding (ROLE) model, which yields two main benefits. First, our model can effectively capture both implicit and explicit hierarchical structures that come from the network topology and category information of nodes, respectively. Second, it can model the asymmetric proximity using rotation transformations. Specifically, we represent each node with a Lorentzian embedding vector, and learn two rotation matrices to reflect the direction of edges. We conduct extensive experiments on four real-world directed graph datasets. Empirical results demonstrate that the proposed approach consistently outperforms various state-of-the-art embedding models. In particular, ROLE achieves HR@1 scores up to 19.8% higher and NDCG@5 scores up to 11.3% higher than the best baselines on the task of node recommendation
UR - http://hdl.handle.net/10754/686283
UR - https://ieeexplore.ieee.org/document/9950308/
UR - http://www.scopus.com/inward/record.url?scp=85142798553&partnerID=8YFLogxK
U2 - 10.1109/TKDE.2022.3221929
DO - 10.1109/TKDE.2022.3221929
M3 - Article
SN - 1558-2191
SP - 1
EP - 14
JO - IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
JF - IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ER -