Towards Learning Disentangled Representations for Time Series

Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Jingchao Ni, Denghui Zhang, Haifeng Chen, Xia Hu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

Promising progress has been made toward learning efficient time series representations in recent years, but the learned representations often lack interpretability and do not encode semantic meanings by the complex interactions of many latent factors. Learning representations that disentangle these latent factors can bring semantic-rich representations of time series and further enhance interpretability. However, directly adopting the sequential models, such as Long Short-Term Memory Variational AutoEncoder (LSTM-VAE), would encounter a Kullback?Leibler (KL) vanishing problem: the LSTM decoder often generates sequential data without efficiently using latent representations, and the latent spaces sometimes could even be independent of the observation space. And traditional disentanglement methods may intensify the trend of KL vanishing along with the disentanglement process, because they tend to penalize the mutual information between the latent space and the observations. In this paper, we propose Disentangle Time-Series, a novel disentanglement enhancement framework for time series data. Our framework achieves multi-level disentanglement by covering both individual latent factors and group semantic segments. We propose augmenting the original VAE objective by decomposing the evidence lower-bound and extracting evidence linking factorial representations to disentanglement. Additionally, we introduce a mutual information maximization term between the observation space to the latent space to alleviate the KL vanishing problem while preserving the disentanglement property. Experimental results on five real-world IoT datasets demonstrate that the representations learned by DTS achieve superior performance in various tasks with better interpretability.

Original languageEnglish (US)
Title of host publicationKDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages3270-3278
Number of pages9
ISBN (Electronic)9781450393850
DOIs
StatePublished - Aug 14 2022
Externally publishedYes
Event28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, United States
Duration: Aug 14 2022Aug 18 2022

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/TerritoryUnited States
CityWashington
Period8/14/228/18/22

All Science Journal Classification (ASJC) codes

  • Software
  • Information Systems

Keywords

  • deep generative model
  • disentangled representation learning
  • domain adaptation
  • interpretable representation
  • time series analysis

Fingerprint

Dive into the research topics of 'Towards Learning Disentangled Representations for Time Series'. Together they form a unique fingerprint.

Cite this