Hyperbolic Graph Attention Network

by   Yiding Zhang, et al.

Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently. However, most of the existing GNN models are primarily designed for graphs in Euclidean spaces. Recent research has proven that the graph data exhibits non-Euclidean latent anatomy. Unfortunately, there was rarely study of GNN in non-Euclidean settings so far. To bridge this gap, in this paper, we study the GNN with attention mechanism in hyperbolic spaces at the first attempt. The research of hyperbolic GNN has some unique challenges: since the hyperbolic spaces are not vector spaces, the vector operations (e.g., vector addition, subtraction, and scalar multiplication) cannot be carried. To tackle this problem, we employ the gyrovector spaces, which provide an elegant algebraic formalism for hyperbolic geometry, to transform the features in a graph; and then we propose the hyperbolic proximity based attention mechanism to aggregate the features. Moreover, as mathematical operations in hyperbolic spaces could be more complicated than those in Euclidean spaces, we further devise a novel acceleration strategy using logarithmic and exponential mappings to improve the efficiency of our proposed model. The comprehensive experimental results on four real-world datasets demonstrate the performance of our proposed hyperbolic graph attention network model, by comparisons with other state-of-the-art baseline methods.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


Lorentzian Graph Convolutional Networks

Graph convolutional networks (GCNs) have received considerable research ...

SI-GAT: A method based on improved Graph Attention Network for sonar image classification

The existing sonar image classification methods based on deep learning a...

Time-aware Hyperbolic Graph Attention Network for Session-based Recommendation

Session-based Recommendation (SBR) is to predict users' next interested ...

The Isoperimetric Problem in a Lattice of H^3

The isoperimetric problem is one of the oldest in geometry and it consis...

PU GNN: Chargeback Fraud Detection in P2E MMORPGs via Graph Attention Networks with Imbalanced PU Labels

The recent advent of play-to-earn (P2E) systems in massively multiplayer...

GNN-based Passenger Request Prediction

Passenger request prediction is essential for operations planning, contr...

Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation

Since Knowledge Graphs (KGs) contain rich semantic information, recently...

Please sign up or login with your details

Forgot password? Click here to reset