EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting

Razvan Gabriel Cirstea, Tung Kieu, Chenjuan Guo, Bin Yang, Sinno Jialin Pan

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

15 Citationer (Scopus)

Abstrakt

Correlated time series forecasting plays an essential role in many cyber-physical systems, where entities interact with each other over time. To enable accurate forecasting, it is essential to capture both the temporal dynamics and the correlations among different entities. To capture the former, two popular types of models, recurrent neural networks (RNNs) and temporal convolution networks (TCNs), are employed. To capture the latter, a graph is constructed to reflect certain relationships among entities and then graph convolution (GC) is applied upon the graph to capture the correlations among the entities. The state-of-the-art forecasting accuracy is achieved by models that combine RNNs or TCNs with GC. However, they neither capture distinct temporal dynamics that exist among different entities nor consider the entity correlations that evolve across time.In this paper, rather than proposing yet another new end-to-end forecasting model, we aim at providing a framework to enhance existing forecasting models, where we propose generic plugins that can be easily integrated into existing solutions to solve the two challenges and thus further enhance their accuracy. Specifically, we propose two plugin neural networks that are able to better capture distinct temporal dynamics for different entities and dynamic entity correlations across time, so that forecasting accuracy is improved while model parameters to be learned are reduced. Experimental results on three real-world correlated time series data sets demonstrate that the proposed framework with the two plugin networks is able to achieve the above goals.

OriginalsprogEngelsk
TitelProceedings of the 37th IEEE International Conference on Data Engineering, ICDE 2021
Antal sider12
ForlagIEEE
Publikationsdatoapr. 2021
Sider1739-1750
Artikelnummer9458855
ISBN (Elektronisk)9781728191843
DOI
StatusUdgivet - apr. 2021
Begivenhed37th IEEE International Conference on Data Engineering, ICDE 2021 - Virtual, Chania, Grækenland
Varighed: 19 apr. 202122 apr. 2021

Konference

Konference37th IEEE International Conference on Data Engineering, ICDE 2021
Land/OmrådeGrækenland
ByVirtual, Chania
Periode19/04/202122/04/2021
NavnProceedings - International Conference on Data Engineering
Vol/bind2021-April
ISSN1084-4627

Bibliografisk note

Funding Information:
This work was supported by Independent Research Fund Denmark under agreements 8022-00246B and 8048-00038B.

Publisher Copyright:
© 2021 IEEE.

Fingeraftryk

Dyk ned i forskningsemnerne om 'EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting'. Sammen danner de et unikt fingeraftryk.

Citationsformater