Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bai, Qijie, Guo, Jiawen, Zhang, Haiwei, Nie, Changli, Zhang, Lin, Yuan, Xiaojie
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2304.06970
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913391445016576
author Bai, Qijie
Guo, Jiawen
Zhang, Haiwei
Nie, Changli
Zhang, Lin
Yuan, Xiaojie
author_facet Bai, Qijie
Guo, Jiawen
Zhang, Haiwei
Nie, Changli
Zhang, Lin
Yuan, Xiaojie
contents Temporal heterogeneous information network (temporal HIN) embedding, aiming to represent various types of nodes of different timestamps into low dimensional spaces while preserving structural and semantic information, is of vital importance in diverse real-life tasks. Researchers have made great efforts on temporal HIN embedding in Euclidean spaces and got some considerable achievements. However, there is always a fundamental conflict that many real-world networks show hierarchical property and power-law distribution, and are not isometric of Euclidean spaces. Recently, representation learning in hyperbolic spaces has been proved to be valid for data with hierarchical and power-law structure. Inspired by this character, we propose a hyperbolic heterogeneous temporal network embedding ($\text{H}^2\text{TNE}$) model for temporal HINs. Specifically, we leverage a temporally and heterogeneously double-constrained random walk strategy to capture the structural and semantic information, and then calculate the embedding by exploiting hyperbolic distance in proximity measurement. Experimental results show that our method has superior performance on temporal link prediction and node classification compared with SOTA models.
format Preprint
id arxiv_https___arxiv_org_abs_2304_06970
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle $\text{H}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
Bai, Qijie
Guo, Jiawen
Zhang, Haiwei
Nie, Changli
Zhang, Lin
Yuan, Xiaojie
Social and Information Networks
Artificial Intelligence
Temporal heterogeneous information network (temporal HIN) embedding, aiming to represent various types of nodes of different timestamps into low dimensional spaces while preserving structural and semantic information, is of vital importance in diverse real-life tasks. Researchers have made great efforts on temporal HIN embedding in Euclidean spaces and got some considerable achievements. However, there is always a fundamental conflict that many real-world networks show hierarchical property and power-law distribution, and are not isometric of Euclidean spaces. Recently, representation learning in hyperbolic spaces has been proved to be valid for data with hierarchical and power-law structure. Inspired by this character, we propose a hyperbolic heterogeneous temporal network embedding ($\text{H}^2\text{TNE}$) model for temporal HINs. Specifically, we leverage a temporally and heterogeneously double-constrained random walk strategy to capture the structural and semantic information, and then calculate the embedding by exploiting hyperbolic distance in proximity measurement. Experimental results show that our method has superior performance on temporal link prediction and node classification compared with SOTA models.
title $\text{H}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
topic Social and Information Networks
Artificial Intelligence
url https://arxiv.org/abs/2304.06970