Multi-View Self-Supervised Learning For Multivariate Variable-Channel Time Series

Research output: Chapter in Book/Report/Conference proceedingBook chapterResearchpeer-review

Abstract

Labeling of multivariate biomedical time series data is a laborious and expensive process. Self-supervised contrastive learning alleviates the need for large, labeled datasets through pretraining on unlabeled data. However, for multivariate time series data, the set of input channels often varies between applications, and most existing work does not allow for transfer between datasets with different sets of input channels. We propose learning one encoder to operate on all input channels individually. We then use a message passing neural network to extract a single representation across channels. We demonstrate the potential of this method by pretraining our model on a dataset with six EEG channels and then fine-tuning it on a dataset with two different EEG channels. We compare models with and without the message passing neural network across different contrastive loss functions. We show that our method, combined with the TS2Vec loss, outperforms all other methods in most settings.
Original languageEnglish
Title of host publicationProceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing
Number of pages6
PublisherIEEE
Publication date2023
ISBN (Print)979-8-3503-2412-9
ISBN (Electronic)979-8-3503-2411-2
DOIs
Publication statusPublished - 2023
Event2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing - Rome, Italy, Rome, Italy
Duration: 17 Sept 202320 Sept 2023

Conference

Conference2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing
LocationRome, Italy
Country/TerritoryItaly
CityRome
Period17/09/202320/09/2023

Keywords

  • Self-supervised learning
  • Message passing neural networks
  • Multi-view learning
  • Multivariate time series
  • Sleeping staging

Fingerprint

Dive into the research topics of 'Multi-View Self-Supervised Learning For Multivariate Variable-Channel Time Series'. Together they form a unique fingerprint.

Cite this