Forecasting interaction order on temporal graphs
Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets a...
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/6134 https://ink.library.smu.edu.sg/context/sis_research/article/7137/viewcontent/3447548.3467341.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-7137 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-71372021-09-29T12:13:21Z Forecasting interaction order on temporal graphs XIA, Wenwen LI, Yuchen TIAN, Jianwei LI, Shenghong Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets appear in sequential orders. And the orders may lead to interesting applications. While a binary link prediction formulation fails to handle such an order-sensitive case. In this paper, we focus on such an interaction order prediction (IOP) problem among a given node set on temporal graphs. For the technical aspect, we develop a graph neural network model named Temporal ATtention network (TAT), which utilizes the finegrained time information on temporal graphs by encoding continuous real-valued timestamps as vectors. For each transformation layer of the model, we devise an attention mechanism to aggregate neighborhoods’ information based on their representations and time encodings attached to their specific edges. We also propose a novel training scheme to address the permutation-sensitive property of the IOP problem. Experiments on several real-world temporal graphs reveal that TAT outperforms some state-of-the-art graph neural networks by 55% on average under the AUC metric. 2021-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6134 info:doi/10.1145/3447548.3467341 https://ink.library.smu.edu.sg/context/sis_research/article/7137/viewcontent/3447548.3467341.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 Graphs Graph Neural Networks Interaction Order Prediction Databases and Information Systems 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 Graphs Graph Neural Networks Interaction Order Prediction Databases and Information Systems Graphics and Human Computer Interfaces OS and Networks |
spellingShingle |
Temporal Graphs Graph Neural Networks Interaction Order Prediction Databases and Information Systems Graphics and Human Computer Interfaces OS and Networks XIA, Wenwen LI, Yuchen TIAN, Jianwei LI, Shenghong Forecasting interaction order on temporal graphs |
description |
Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets appear in sequential orders. And the orders may lead to interesting applications. While a binary link prediction formulation fails to handle such an order-sensitive case. In this paper, we focus on such an interaction order prediction (IOP) problem among a given node set on temporal graphs. For the technical aspect, we develop a graph neural network model named Temporal ATtention network (TAT), which utilizes the finegrained time information on temporal graphs by encoding continuous real-valued timestamps as vectors. For each transformation layer of the model, we devise an attention mechanism to aggregate neighborhoods’ information based on their representations and time encodings attached to their specific edges. We also propose a novel training scheme to address the permutation-sensitive property of the IOP problem. Experiments on several real-world temporal graphs reveal that TAT outperforms some state-of-the-art graph neural networks by 55% on average under the AUC metric. |
format |
text |
author |
XIA, Wenwen LI, Yuchen TIAN, Jianwei LI, Shenghong |
author_facet |
XIA, Wenwen LI, Yuchen TIAN, Jianwei LI, Shenghong |
author_sort |
XIA, Wenwen |
title |
Forecasting interaction order on temporal graphs |
title_short |
Forecasting interaction order on temporal graphs |
title_full |
Forecasting interaction order on temporal graphs |
title_fullStr |
Forecasting interaction order on temporal graphs |
title_full_unstemmed |
Forecasting interaction order on temporal graphs |
title_sort |
forecasting interaction order on temporal graphs |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/6134 https://ink.library.smu.edu.sg/context/sis_research/article/7137/viewcontent/3447548.3467341.pdf |
_version_ |
1770575834552205312 |