Multi-Hyperbolic Space-based Heterogeneous Graph Attention Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jongmin, Han, Seunghoon, Lee, Jong-Ryul, Lim, Sungsu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911014559154176
author Park, Jongmin
Han, Seunghoon
Lee, Jong-Ryul
Lim, Sungsu
author_facet Park, Jongmin
Han, Seunghoon
Lee, Jong-Ryul
Lim, Sungsu
contents To leverage the complex structures within heterogeneous graphs, recent studies on heterogeneous graph embedding use a hyperbolic space, characterized by a constant negative curvature and exponentially increasing space, which aligns with the structural properties of heterogeneous graphs. However, despite heterogeneous graphs inherently possessing diverse power-law structures, most hyperbolic heterogeneous graph embedding models use a single hyperbolic space for the entire heterogeneous graph, which may not effectively capture the diverse power-law structures within the heterogeneous graph. To address this limitation, we propose Multi-hyperbolic Space-based heterogeneous Graph Attention Network (MSGAT), which uses multiple hyperbolic spaces to effectively capture diverse power-law structures within heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness of MSGAT. The experimental results demonstrate that MSGAT outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11283
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Hyperbolic Space-based Heterogeneous Graph Attention Network
Park, Jongmin
Han, Seunghoon
Lee, Jong-Ryul
Lim, Sungsu
Machine Learning
Artificial Intelligence
To leverage the complex structures within heterogeneous graphs, recent studies on heterogeneous graph embedding use a hyperbolic space, characterized by a constant negative curvature and exponentially increasing space, which aligns with the structural properties of heterogeneous graphs. However, despite heterogeneous graphs inherently possessing diverse power-law structures, most hyperbolic heterogeneous graph embedding models use a single hyperbolic space for the entire heterogeneous graph, which may not effectively capture the diverse power-law structures within the heterogeneous graph. To address this limitation, we propose Multi-hyperbolic Space-based heterogeneous Graph Attention Network (MSGAT), which uses multiple hyperbolic spaces to effectively capture diverse power-law structures within heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness of MSGAT. The experimental results demonstrate that MSGAT outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.
title Multi-Hyperbolic Space-based Heterogeneous Graph Attention Network
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.11283