English

Self-Distilled Representation Learning for Time Series

Machine Learning 2023-11-21 v1

Abstract

Self-supervised learning for time-series data holds potential similar to that recently unleashed in Natural Language Processing and Computer Vision. While most existing works in this area focus on contrastive learning, we propose a conceptually simple yet powerful non-contrastive approach, based on the data2vec self-distillation framework. The core of our method is a student-teacher scheme that predicts the latent representation of an input time series from masked views of the same time series. This strategy avoids strong modality-specific assumptions and biases typically introduced by the design of contrastive sample pairs. We demonstrate the competitiveness of our approach for classification and forecasting as downstream tasks, comparing with state-of-the-art self-supervised learning methods on the UCR and UEA archives as well as the ETT and Electricity datasets.

Keywords

Cite

@article{arxiv.2311.11335,
  title  = {Self-Distilled Representation Learning for Time Series},
  author = {Felix Pieper and Konstantin Ditschuneit and Martin Genzel and Alexandra Lindt and Johannes Otterbach},
  journal= {arXiv preprint arXiv:2311.11335},
  year   = {2023}
}

Comments

Presented at the NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice

R2 v1 2026-06-28T13:25:24.985Z