Dynamic heterogeneous graph embedding via heterogeneous Hawkes process
Graph embedding, aiming to learn low-dimensional representations of nodes while preserving valuable structure information, has played a key role in graph analysis and inference. However, most existing methods deal with static homogeneous topologies, while graphs in real-world scenarios are gradually...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6877 https://ink.library.smu.edu.sg/context/sis_research/article/7880/viewcontent/Dynamic_Heterogeneous_Graph_Embedding_via_Heterogeneous_Hawkes_Process.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-7880 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-78802022-02-07T11:06:11Z Dynamic heterogeneous graph embedding via heterogeneous Hawkes process JI, Yugang JIA, Tianrui FANG, Yuan SHI, Chuan Graph embedding, aiming to learn low-dimensional representations of nodes while preserving valuable structure information, has played a key role in graph analysis and inference. However, most existing methods deal with static homogeneous topologies, while graphs in real-world scenarios are gradually generated with different-typed temporal events, containing abundant semantics and dynamics. Limited work has been done for embedding dynamic heterogeneous graphs since it is very challenging to model the complete formation process of heterogeneous events. In this paper, we propose a novel Heterogeneous Hawkes Process based dynamic Graph Embedding (HPGE) to handle this problem. HPGE effectively integrates the Hawkes process into graph embedding to capture the excitation of various historical events on the current type-wise events. Specifically, HPGE first designs a heterogeneous conditional intensity to model the base rate and temporal influence caused by heterogeneous historical events. Then the heterogeneous evolved attention mechanism is designed to determine the fine-grained excitation to different-typed current events. Besides, we deploy the temporal importance sampling strategy to sample representative events for efficient excitation propagation. Experimental results demonstrate that HPGE consistently outperforms the state-of-the-art alternatives. 2021-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6877 info:doi/10.1007/978-3-030-86486-6_24 https://ink.library.smu.edu.sg/context/sis_research/article/7880/viewcontent/Dynamic_Heterogeneous_Graph_Embedding_via_Heterogeneous_Hawkes_Process.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 dynamic heterogeneous graph graph embedding heterogeneous Hawkes process heterogeneous evolved attention mechanism Artificial Intelligence and Robotics 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 |
dynamic heterogeneous graph graph embedding heterogeneous Hawkes process heterogeneous evolved attention mechanism Artificial Intelligence and Robotics Databases and Information Systems |
spellingShingle |
dynamic heterogeneous graph graph embedding heterogeneous Hawkes process heterogeneous evolved attention mechanism Artificial Intelligence and Robotics Databases and Information Systems JI, Yugang JIA, Tianrui FANG, Yuan SHI, Chuan Dynamic heterogeneous graph embedding via heterogeneous Hawkes process |
description |
Graph embedding, aiming to learn low-dimensional representations of nodes while preserving valuable structure information, has played a key role in graph analysis and inference. However, most existing methods deal with static homogeneous topologies, while graphs in real-world scenarios are gradually generated with different-typed temporal events, containing abundant semantics and dynamics. Limited work has been done for embedding dynamic heterogeneous graphs since it is very challenging to model the complete formation process of heterogeneous events. In this paper, we propose a novel Heterogeneous Hawkes Process based dynamic Graph Embedding (HPGE) to handle this problem. HPGE effectively integrates the Hawkes process into graph embedding to capture the excitation of various historical events on the current type-wise events. Specifically, HPGE first designs a heterogeneous conditional intensity to model the base rate and temporal influence caused by heterogeneous historical events. Then the heterogeneous evolved attention mechanism is designed to determine the fine-grained excitation to different-typed current events. Besides, we deploy the temporal importance sampling strategy to sample representative events for efficient excitation propagation. Experimental results demonstrate that HPGE consistently outperforms the state-of-the-art alternatives. |
format |
text |
author |
JI, Yugang JIA, Tianrui FANG, Yuan SHI, Chuan |
author_facet |
JI, Yugang JIA, Tianrui FANG, Yuan SHI, Chuan |
author_sort |
JI, Yugang |
title |
Dynamic heterogeneous graph embedding via heterogeneous Hawkes process |
title_short |
Dynamic heterogeneous graph embedding via heterogeneous Hawkes process |
title_full |
Dynamic heterogeneous graph embedding via heterogeneous Hawkes process |
title_fullStr |
Dynamic heterogeneous graph embedding via heterogeneous Hawkes process |
title_full_unstemmed |
Dynamic heterogeneous graph embedding via heterogeneous Hawkes process |
title_sort |
dynamic heterogeneous graph embedding via heterogeneous hawkes process |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/6877 https://ink.library.smu.edu.sg/context/sis_research/article/7880/viewcontent/Dynamic_Heterogeneous_Graph_Embedding_via_Heterogeneous_Hawkes_Process.pdf |
_version_ |
1770576111738028032 |