pith. sign in

arxiv: 2106.10466 · v4 · pith:3KRO7FSEnew · submitted 2021-06-19 · 💻 cs.LG · cs.AI

TS2Vec: Towards Universal Representation of Time Series

Zhihan Yue , Yujing Wang , Juanyong Duan , Tianmeng Yang , Congrui Huang , Yunhai Tong , Bixiong Xu This is my paper
classification 💻 cs.LG cs.AI
keywords seriestimerepresentationsts2vecrepresentationlearnedanomalyapply
0
0 comments X
read the original abstract

This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp. Furthermore, to obtain the representation of an arbitrary sub-sequence in the time series, we can apply a simple aggregation over the representations of corresponding timestamps. We conduct extensive experiments on time series classification tasks to evaluate the quality of time series representations. As a result, TS2Vec achieves significant improvement over existing SOTAs of unsupervised time series representation on 125 UCR datasets and 29 UEA datasets. The learned timestamp-level representations also achieve superior results in time series forecasting and anomaly detection tasks. A linear regression trained on top of the learned representations outperforms previous SOTAs of time series forecasting. Furthermore, we present a simple way to apply the learned representations for unsupervised anomaly detection, which establishes SOTA results in the literature. The source code is publicly available at https://github.com/yuezhihan/ts2vec.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data

    cs.LG 2026-05 unverdicted novelty 7.0

    ProtoSSL discovers generalizable prototypes from unlabeled time-series via self-supervision and assigns them to new tasks for interpretable predictions, outperforming supervised baselines in low-data regimes on ECG datasets.

  2. Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations

    cs.LG 2026-07 unverdicted novelty 6.0

    Aionoscope shows that time-series representations recover coarse signal types reliably but expose dense latent states like phase and amplitude much less reliably, with best dense-probe R² at 0.689 versus oracle 0.999.

  3. Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA

    astro-ph.IM 2026-06 unverdicted novelty 6.0

    A JEPA-based model with domain-informed multi-view self-distillation learns light-curve representations that outperform hand-crafted features on 15 of 16 StarEmbed metrics and adapts competitively to other irregular t...

  4. StarCLR: Contrastive Learning Representation for Astronomical Light Curves

    astro-ph.SR 2026-04 conditional novelty 6.0

    StarCLR pretrains on TESS light curves via contrastive learning on overlapping subsequences and improves variable star classification F1 scores over scratch-trained models when fine-tuned on TESS, ZTF, and Gaia.

  5. LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning

    cs.LG 2026-07 unverdicted novelty 5.0

    LeNEPA proposes a no-augmentation next-latent prediction recipe that maintains frozen-probe performance across ECG and synthetic diagnostic time-series datasets under fixed-recipe conditions where a tuned JEPA baselin...

  6. Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning

    cs.LG 2026-07 unverdicted novelty 4.0

    Active learning with masked reconstruction and minimax training raises AUC by 12.39% across 28 test cases on four multivariate datasets and seven unsupervised backbones.