English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Time series forecasting plays a key role in a variety of domains. In a lot ofreal-world scenarios, there exist multiple forecasting entities (e.g. powerstation in the solar system, stations in the traffic system). A straightforwardforecasting solution is to mine the temporal dependency for each individualentity through 1d-CNN, RNN, transformer, etc. This approach overlooks therelations between these entities and, in consequence, loses the opportunity toimprove performance using spatial-temporal relation. However, in manyreal-world scenarios, beside explicit relation, there could exist crucial yetimplicit relation between entities. How to discover the useful implicitrelation between entities and effectively utilize the relations for each entityunder various circumstances is crucial. In order to mine the implicit relationbetween entities as much as possible and dynamically utilize the relation toimprove the forecasting performance, we propose an attentional multi-graphneural network with automatic graph learning (A2GNN) in this work.Particularly, a Gumbel-softmax based auto graph learner is designed toautomatically capture the implicit relation among forecasting entities. Wefurther propose an attentional relation learner that enables every entity todynamically pay attention to its preferred relations. Extensive experiments areconducted on five real-world datasets from three different domains. The resultsdemonstrate the effectiveness of A2GNN beyond several state-of-the-art methods.

Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting