Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Zhe, Zhou, Sheng, Chen, Jiawei, Zhang, Zhen, Hu, Binbin, Feng, Yan, Chen, Chun, Wang, Can
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2407.16959
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910727745306624
author Wang, Zhe
Zhou, Sheng
Chen, Jiawei
Zhang, Zhen
Hu, Binbin
Feng, Yan
Chen, Chun
Wang, Can
author_facet Wang, Zhe
Zhou, Sheng
Chen, Jiawei
Zhang, Zhen
Hu, Binbin
Feng, Yan
Chen, Chun
Wang, Can
contents Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial requirement for representation learning in CTDGs is the appropriate estimation and preservation of proximity. However, due to the sparse and evolving characteristics of CTDGs, the spatial-temporal properties inherent in high-order proximity remain largely unexplored. Despite its importance, this property presents significant challenges due to the computationally intensive nature of personalized interaction intensity estimation and the dynamic attributes of CTDGs. To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process. Building on this, we introduce the Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding (CorDGT), which efficiently retains the evolving spatial-temporal high-order proximity for effective node representation learning in CTDGs. Extensive experiments on seven small and two large-scale datasets demonstrate the superior performance and scalability of the proposed CorDGT. The code is available at: https://github.com/wangz3066/CorDGT.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16959
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding
Wang, Zhe
Zhou, Sheng
Chen, Jiawei
Zhang, Zhen
Hu, Binbin
Feng, Yan
Chen, Chun
Wang, Can
Machine Learning
Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling complex interactions between nodes. A fundamental and crucial requirement for representation learning in CTDGs is the appropriate estimation and preservation of proximity. However, due to the sparse and evolving characteristics of CTDGs, the spatial-temporal properties inherent in high-order proximity remain largely unexplored. Despite its importance, this property presents significant challenges due to the computationally intensive nature of personalized interaction intensity estimation and the dynamic attributes of CTDGs. To this end, we propose a novel Correlated Spatial-Temporal Positional encoding that incorporates a parameter-free personalized interaction intensity estimation under the weak assumption of the Poisson Point Process. Building on this, we introduce the Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding (CorDGT), which efficiently retains the evolving spatial-temporal high-order proximity for effective node representation learning in CTDGs. Extensive experiments on seven small and two large-scale datasets demonstrate the superior performance and scalability of the proposed CorDGT. The code is available at: https://github.com/wangz3066/CorDGT.
title Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding
topic Machine Learning
url https://arxiv.org/abs/2407.16959