# A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning

arXiv: https://arxiv.org/abs/2305.18888 · HTML: https://mlsanity.com/paper/2305.18888/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 68 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training](https://mlsanity.com/paper/2006.09963/) (2020)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Vision-Language Pre-Training with Triple Contrastive Learning](https://mlsanity.com/paper/2202.10401/) (2022)
- [A Survey on Multi-view Learning](https://mlsanity.com/paper/1304.5634/) (2013)
- [Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks](https://mlsanity.com/paper/1706.00527/) (2017)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [Multivariate LSTM-FCNs for Time Series Classification](https://mlsanity.com/paper/1801.04503/) (2018)
- [Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://mlsanity.com/paper/2202.04770/) (2022)
- [Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification](https://mlsanity.com/paper/2002.10061/) (2020)
- [Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2206.13816/) (2022)
- [UniVIP: A Unified Framework for Self-Supervised Visual Pre-training](https://mlsanity.com/paper/2203.06965/) (2022)
- [Dynamic Sparse Network for Time Series Classification: Learning What to "see''](https://mlsanity.com/paper/2212.09840/) (2022)

## Built on by (most cited first, 9 of 9)

- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [UniCL: A Universal Contrastive Learning Framework for Large Time Series Models](https://mlsanity.com/paper/2405.10597/) (2024)
- [TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis](https://mlsanity.com/paper/2404.05057/) (2024)
- [CAP: Towards PPG Universal Representation Learning with Patient-level Supervision](https://mlsanity.com/paper/2606.15284/) (2026)
- [KDSelector: A Knowledge-Enhanced and Data-Efficient Model Selector Learning Framework for Time Series Anomaly Detection](https://mlsanity.com/paper/2503.12478/) (2025)
- [Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning](https://mlsanity.com/paper/2312.05698/) (2023)
- [Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning](https://mlsanity.com/paper/2603.18941/) (2026)
- [TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version](https://mlsanity.com/paper/2606.02142/) (2026)
- [Time series generation with spectrally aligned latent flow matching](https://mlsanity.com/paper/2609.21989/) (2026)

## Abstract (arXiv)

Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible labels. However, existing approaches usually adopt the models originally designed for other domains (e.g., computer vision) to encode the time series data and {rely on strong assumptions to design learning objectives, which limits their ability to perform well}. To deal with these problems, we propose a novel URL framework for multivariate time series by learning time-series-specific shapelet-based representation through a popular contrasting learning paradigm. To the best of our knowledge, this is the first work that explores the shapelet-based embedding in the unsupervised general-purpose representation learning. A unified shapelet-based encoder and a novel learning objective with multi-grained contrasting and multi-scale alignment are particularly designed to achieve our goal, and a data augmentation library is employed to improve the generalization. We conduct extensive experiments using tens of real-world datasets to assess the representation quality on many downstream tasks, including classification, clustering, and anomaly detection. The results demonstrate the superiority of our method against not only URL competitors, but also techniques specially designed for downstream tasks. Our code has been made publicly available at https://github.com/real2fish/CSL.