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

Sensors in cyber-physical systems often capture interconnected processes andthus emit correlated time series (CTS), the forecasting of which enablesimportant applications. The key to successful CTS forecasting is to uncover thetemporal dynamics of time series and the spatial correlations among timeseries. Deep learning-based solutions exhibit impressive performance atdiscerning these aspects. In particular, automated CTS forecasting, where thedesign of an optimal deep learning architecture is automated, enablesforecasting accuracy that surpasses what has been achieved by manualapproaches. However, automated CTS solutions remain in their infancy and areonly able to find optimal architectures for predefined hyperparameters andscale poorly to large-scale CTS. To overcome these limitations, we proposeSEARCH, a joint, scalable framework, to automatically devise effective CTSforecasting models. Specifically, we encode each candidate architecture andaccompanying hyperparameters into a joint graph representation. We introduce anefficient Architecture-Hyperparameter Comparator (AHC) to rank allarchitecture-hyperparameter pairs, and we then further evaluate the top-rankedpairs to select a final result. Extensive experiments on six benchmark datasetsdemonstrate that SEARCH not only eliminates manual efforts but also is capableof better performance than manually designed and existing automaticallydesigned CTS models. In addition, it shows excellent scalability to large CTS.

Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting