Topic-aware heterogeneous graph neural network for link prediction

Heterogeneous graphs (HGs), consisting of multiple types of nodes and links, can characterize a variety of real-world complex systems. Recently, heterogeneous graph neural networks (HGNNs), as a powerful graph embedding method to aggregate heterogeneous structure and attribute information, has earne...

Full description

Saved in:
Bibliographic Details
Main Authors: XU, Siyong, YANG, Cheng, FANG, Yuan, TIANCHI, Yang, ZHANG, Luhao
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6805
https://ink.library.smu.edu.sg/context/sis_research/article/7808/viewcontent/123.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-7808
record_format dspace
spelling sg-smu-ink.sis_research-78082022-01-27T08:30:38Z Topic-aware heterogeneous graph neural network for link prediction XU, Siyong YANG, Cheng FANG, Yuan FANG, Yuan TIANCHI, Yang ZHANG, Luhao Heterogeneous graphs (HGs), consisting of multiple types of nodes and links, can characterize a variety of real-world complex systems. Recently, heterogeneous graph neural networks (HGNNs), as a powerful graph embedding method to aggregate heterogeneous structure and attribute information, has earned a lot of attention. Despite the ability of HGNNs in capturing rich semantics which reveal different aspects of nodes, they still stay at a coarse-grained level which simply exploits structural characteristics. In fact, rich unstructured text content of nodes also carries latent but more fine-grained semantics arising from multi-facet topic-aware factors, which fundamentally manifest why nodes of different types would connect and form a specific heterogeneous structure. However, little effort has been devoted to factorizing them.In this paper, we propose a Topic-aware Heterogeneous Graph Neural Network, named THGNN, to hierarchically mine topic-aware semantics for learning multi-facet node representations for link prediction in HGs. Specifically, our model mainly applies an alternating two-step aggregation mechanism including intra-metapath decomposition and inter-metapath mergence, which can distinctively aggregate rich heterogeneous information according to the inferential topic-aware factors and preserve hierarchical semantics. Furthermore, a topic prior guidance module is also designed to keep the quality of multi-facet topic-aware embeddings relying on the global knowledge from unstructured text content in HGs. It helps to simultaneously improve both performance and interpretability. Experimental results on three real-world HGs demonstrate that our proposed model can effectively outperform the state-of-the-art methods in the link prediction task, and show the potential interpretability of learnt multi-facet topic-aware representations. 2021-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6805 info:doi/10.1145/3459637.3482485 https://ink.library.smu.edu.sg/context/sis_research/article/7808/viewcontent/123.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 Heterogeneous graph Graph neural networks Representation learning Link prediction Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Heterogeneous graph
Graph neural networks
Representation learning
Link prediction
Databases and Information Systems
spellingShingle Heterogeneous graph
Graph neural networks
Representation learning
Link prediction
Databases and Information Systems
XU, Siyong
YANG, Cheng
FANG, Yuan
FANG, Yuan
TIANCHI, Yang
ZHANG, Luhao
Topic-aware heterogeneous graph neural network for link prediction
description Heterogeneous graphs (HGs), consisting of multiple types of nodes and links, can characterize a variety of real-world complex systems. Recently, heterogeneous graph neural networks (HGNNs), as a powerful graph embedding method to aggregate heterogeneous structure and attribute information, has earned a lot of attention. Despite the ability of HGNNs in capturing rich semantics which reveal different aspects of nodes, they still stay at a coarse-grained level which simply exploits structural characteristics. In fact, rich unstructured text content of nodes also carries latent but more fine-grained semantics arising from multi-facet topic-aware factors, which fundamentally manifest why nodes of different types would connect and form a specific heterogeneous structure. However, little effort has been devoted to factorizing them.In this paper, we propose a Topic-aware Heterogeneous Graph Neural Network, named THGNN, to hierarchically mine topic-aware semantics for learning multi-facet node representations for link prediction in HGs. Specifically, our model mainly applies an alternating two-step aggregation mechanism including intra-metapath decomposition and inter-metapath mergence, which can distinctively aggregate rich heterogeneous information according to the inferential topic-aware factors and preserve hierarchical semantics. Furthermore, a topic prior guidance module is also designed to keep the quality of multi-facet topic-aware embeddings relying on the global knowledge from unstructured text content in HGs. It helps to simultaneously improve both performance and interpretability. Experimental results on three real-world HGs demonstrate that our proposed model can effectively outperform the state-of-the-art methods in the link prediction task, and show the potential interpretability of learnt multi-facet topic-aware representations.
format text
author XU, Siyong
YANG, Cheng
FANG, Yuan
FANG, Yuan
TIANCHI, Yang
ZHANG, Luhao
author_facet XU, Siyong
YANG, Cheng
FANG, Yuan
FANG, Yuan
TIANCHI, Yang
ZHANG, Luhao
author_sort XU, Siyong
title Topic-aware heterogeneous graph neural network for link prediction
title_short Topic-aware heterogeneous graph neural network for link prediction
title_full Topic-aware heterogeneous graph neural network for link prediction
title_fullStr Topic-aware heterogeneous graph neural network for link prediction
title_full_unstemmed Topic-aware heterogeneous graph neural network for link prediction
title_sort topic-aware heterogeneous graph neural network for link prediction
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/6805
https://ink.library.smu.edu.sg/context/sis_research/article/7808/viewcontent/123.pdf
_version_ 1770576072250753024