Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

8-2023

Abstract

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.

Keywords

temporal event forecasting, temporal knowledge graph, graph neural network, graph disentanglement

Discipline

Computer Sciences | Digital Communications and Networking

Publication

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

First Page

1643

Last Page

1652

Identifier

10.1145/3580305.3599285

Publisher

ACM

City or Country

United States

Additional URL

https://doi.org/10.1145/3580305.3599285

Download

Share

COinS