Context-aware event forecasting via graph disentanglement
Event forecasting has been a demanding and challenging task throughout the entire human history. It plays a pivotal role in crisis alarming and disaster prevention in various aspects of the whole society. The task of event forecasting aims to model the relational and temporal patterns based on histo...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8289 https://ink.library.smu.edu.sg/context/sis_research/article/9292/viewcontent/2308.06480.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-9292 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-92922023-11-10T08:24:58Z Context-aware event forecasting via graph disentanglement MA, Yunshan YE, Chenchen WU, Zijian WANG, Xiang CAO, Yixin CHUA, Tat-Seng Event forecasting has been a demanding and challenging task throughout the entire human history. It plays a pivotal role in crisis alarming and disaster prevention in various aspects of the whole society. The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future. Most existing studies on event forecasting formulate it as a problem of link prediction on temporal event graphs. However, such pure structured formulation suffers from two main limitations: 1) most events fall into general and high-level types in the event ontology, and therefore they tend to be coarse-grained and offers little utility which inevitably harms the forecasting accuracy; and 2) the events defined by a fixed ontology are unable to retain the out-of-ontology contextual information.To address these limitations, we propose a novel task of context-aware event forecasting which incorporates auxiliary contextual information. First, the categorical context provides supplementary fine-grained information to the coarse-grained events. Second and more importantly, the context provides additional information towards specific situation and condition, which is crucial or even determinant to what will happen next. However, it is challenging to properly integrate context into the event forecasting framework, considering the complex patterns in the multi-context scenario. Towards this end, we design a novel framework named Separation and Collaboration Graph Disentanglement (short as SeCoGD) for context-aware event forecasting. In the separation stage, we leverage the context as a prior guidance to disentangle the event graph into multiple sub-graphs, followed by a context-specific module to model the relational-temporal patterns within each context. In the collaboration stage, we design a cross-context module to retain the collaborative associations among multiple contexts. Since there is no available dataset for this novel task, we construct three large- scale datasets based on GDELT. Experimental results demonstrate hat our model outperforms a list of SOTA methods. The dataset and code are released via https://github.com/yecchen/SeCoGD. 2023-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8289 info:doi/10.1145/3580305.3599285 https://ink.library.smu.edu.sg/context/sis_research/article/9292/viewcontent/2308.06480.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 event forecasting temporal knowledge graph graph neural network graph disentanglement Computer Sciences Digital Communications and Networking |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
temporal event forecasting temporal knowledge graph graph neural network graph disentanglement Computer Sciences Digital Communications and Networking |
spellingShingle |
temporal event forecasting temporal knowledge graph graph neural network graph disentanglement Computer Sciences Digital Communications and Networking MA, Yunshan YE, Chenchen WU, Zijian WANG, Xiang CAO, Yixin CHUA, Tat-Seng Context-aware event forecasting via graph disentanglement |
description |
Event forecasting has been a demanding and challenging task throughout the entire human history. It plays a pivotal role in crisis alarming and disaster prevention in various aspects of the whole society. The task of event forecasting aims to model the relational and temporal patterns based on historical events and makes forecasting to what will happen in the future. Most existing studies on event forecasting formulate it as a problem of link prediction on temporal event graphs. However, such pure structured formulation suffers from two main limitations: 1) most events fall into general and high-level types in the event ontology, and therefore they tend to be coarse-grained and offers little utility which inevitably harms the forecasting accuracy; and 2) the events defined by a fixed ontology are unable to retain the out-of-ontology contextual information.To address these limitations, we propose a novel task of context-aware event forecasting which incorporates auxiliary contextual information. First, the categorical context provides supplementary fine-grained information to the coarse-grained events. Second and more importantly, the context provides additional information towards specific situation and condition, which is crucial or even determinant to what will happen next. However, it is challenging to properly integrate context into the event forecasting framework, considering the complex patterns in the multi-context scenario. Towards this end, we design a novel framework named Separation and Collaboration Graph Disentanglement (short as SeCoGD) for context-aware event forecasting. In the separation stage, we leverage the context as a prior guidance to disentangle the event graph into multiple sub-graphs, followed by a context-specific module to model the relational-temporal patterns within each context. In the collaboration stage, we design a cross-context module to retain the collaborative associations among multiple contexts. Since there is no available dataset for this novel task, we construct three large- scale datasets based on GDELT. Experimental results demonstrate hat our model outperforms a list of SOTA methods. The dataset and code are released via https://github.com/yecchen/SeCoGD. |
format |
text |
author |
MA, Yunshan YE, Chenchen WU, Zijian WANG, Xiang CAO, Yixin CHUA, Tat-Seng |
author_facet |
MA, Yunshan YE, Chenchen WU, Zijian WANG, Xiang CAO, Yixin CHUA, Tat-Seng |
author_sort |
MA, Yunshan |
title |
Context-aware event forecasting via graph disentanglement |
title_short |
Context-aware event forecasting via graph disentanglement |
title_full |
Context-aware event forecasting via graph disentanglement |
title_fullStr |
Context-aware event forecasting via graph disentanglement |
title_full_unstemmed |
Context-aware event forecasting via graph disentanglement |
title_sort |
context-aware event forecasting via graph disentanglement |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8289 https://ink.library.smu.edu.sg/context/sis_research/article/9292/viewcontent/2308.06480.pdf |
_version_ |
1783955666402017280 |