A Dilated Transformer Network for Time Series Anomaly Detection

  • Bo Wu
  • , Zhenjie Yao
  • , Yanhui Tu
  • , Yixin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Unsupervised anomaly detection for time series has been an active research area due to its enormous potential for wireless network management. Existing works have made extraordinary progress in time series representation, reconstruction and forecasting. However, long-term temporal patterns prohibit the model from learning reliable dependencies. To this end, we propose a novel approach based on Transformer with dilated convolution for time anomaly detection. Specifically, we provide a dilated convolution module to extract long-term dependence features. Extensive experiments on various public benchmarks demonstrate that our method has achieved the state-of-the-art performance.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022
EditorsMarek Reformat, Du Zhang, Nikolaos G. Bourbakis
PublisherIEEE Computer Society
Pages48-52
Number of pages5
ISBN (Electronic)9798350397444
DOIs
StatePublished - 2022
Event34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022 - Virtual, Online, China
Duration: Oct 31 2022Nov 2 2022

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume2022-October
ISSN (Print)1082-3409

Conference

Conference34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022
Country/TerritoryChina
CityVirtual, Online
Period10/31/2211/2/22

Keywords

  • anomaly detection
  • dilated convolution
  • time series
  • Transformer

Fingerprint

Dive into the research topics of 'A Dilated Transformer Network for Time Series Anomaly Detection'. Together they form a unique fingerprint.

Cite this