Dynamic meta-path guided temporal heterogeneous graph neural networks

Graph Neural Networks (GNNs) have become the de facto standard for representation learning on topological graphs, which usually derive effective node representations via message passing from neighborhoods. Although GNNs have achieved great success, previous models are mostly confined to static and h...

Full description

Saved in:
Bibliographic Details
Main Authors: JI, Yugang, SHI, Chuan, FANG, Yuan
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8926
https://ink.library.smu.edu.sg/context/sis_research/article/9929/viewcontent/DyMGNN.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9929
record_format dspace
spelling sg-smu-ink.sis_research-99292024-06-27T07:44:34Z Dynamic meta-path guided temporal heterogeneous graph neural networks JI, Yugang SHI, Chuan FANG, Yuan Graph Neural Networks (GNNs) have become the de facto standard for representation learning on topological graphs, which usually derive effective node representations via message passing from neighborhoods. Although GNNs have achieved great success, previous models are mostly confined to static and homogeneous graphs. However, there are multiple dynamic interactions between different-typed nodes in real-world scenarios like academic networks and e-commerce platforms, forming temporal heterogeneous graphs (THGs). Limited work has been done for representation learning on THGs and the challenges are in two aspects. First, there are abundant dynamic semantics between nodes while traditional techniques like meta-paths can only capture static relevance. Second, different semantics on THGs have often mutually evolved with each other over time, making it more difficult than dynamic homogeneous graph modeling. To address this problem, here we propose the Dynamic Meta-path guided temporal heterogeneous Graph Neural Networks (DyMGNNs). To handle the dynamic semantics, we introduce the concept of dynamic meta-path which is a common base for temporal semantic search engines, and then adopt the temporal importance sampling to extract neighborhoods with temporal bias. Focusing on mutual evolution, we design the heterogeneous mutual evolution attention mechanism, which can model the fine-grained interplay of semanticlevel preferences for each node. Extensive experiments on three real-world datasets for node classification and temporal link prediction demonstrate that our method consistently outperforms state-of-the-art alternatives. 2024-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8926 info:doi/10.1142/S2811032323500029 https://ink.library.smu.edu.sg/context/sis_research/article/9929/viewcontent/DyMGNN.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Temporal heterogeneous graph graph neural network dynamic meta-path temporal importance sampling heterogeneous mutual evolution attention Graphics and Human Computer Interfaces OS and Networks
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Temporal heterogeneous graph
graph neural network
dynamic meta-path
temporal importance sampling
heterogeneous mutual evolution attention
Graphics and Human Computer Interfaces
OS and Networks
spellingShingle Temporal heterogeneous graph
graph neural network
dynamic meta-path
temporal importance sampling
heterogeneous mutual evolution attention
Graphics and Human Computer Interfaces
OS and Networks
JI, Yugang
SHI, Chuan
FANG, Yuan
Dynamic meta-path guided temporal heterogeneous graph neural networks
description Graph Neural Networks (GNNs) have become the de facto standard for representation learning on topological graphs, which usually derive effective node representations via message passing from neighborhoods. Although GNNs have achieved great success, previous models are mostly confined to static and homogeneous graphs. However, there are multiple dynamic interactions between different-typed nodes in real-world scenarios like academic networks and e-commerce platforms, forming temporal heterogeneous graphs (THGs). Limited work has been done for representation learning on THGs and the challenges are in two aspects. First, there are abundant dynamic semantics between nodes while traditional techniques like meta-paths can only capture static relevance. Second, different semantics on THGs have often mutually evolved with each other over time, making it more difficult than dynamic homogeneous graph modeling. To address this problem, here we propose the Dynamic Meta-path guided temporal heterogeneous Graph Neural Networks (DyMGNNs). To handle the dynamic semantics, we introduce the concept of dynamic meta-path which is a common base for temporal semantic search engines, and then adopt the temporal importance sampling to extract neighborhoods with temporal bias. Focusing on mutual evolution, we design the heterogeneous mutual evolution attention mechanism, which can model the fine-grained interplay of semanticlevel preferences for each node. Extensive experiments on three real-world datasets for node classification and temporal link prediction demonstrate that our method consistently outperforms state-of-the-art alternatives.
format text
author JI, Yugang
SHI, Chuan
FANG, Yuan
author_facet JI, Yugang
SHI, Chuan
FANG, Yuan
author_sort JI, Yugang
title Dynamic meta-path guided temporal heterogeneous graph neural networks
title_short Dynamic meta-path guided temporal heterogeneous graph neural networks
title_full Dynamic meta-path guided temporal heterogeneous graph neural networks
title_fullStr Dynamic meta-path guided temporal heterogeneous graph neural networks
title_full_unstemmed Dynamic meta-path guided temporal heterogeneous graph neural networks
title_sort dynamic meta-path guided temporal heterogeneous graph neural networks
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/8926
https://ink.library.smu.edu.sg/context/sis_research/article/9929/viewcontent/DyMGNN.pdf
_version_ 1814047633094737920