# Multi-Granularity Framework for Unsupervised Representation Learning of Time Series

arXiv: https://arxiv.org/abs/2312.07248 · HTML: https://mlsanity.com/paper/2312.07248/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data](https://mlsanity.com/paper/2001.07966/) (2020)
- [LSTM Fully Convolutional Networks for Time Series Classification](https://mlsanity.com/paper/1709.05206/) (2017)
- [TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classification](https://mlsanity.com/paper/1906.10329/) (2019)
- [Vision Transformers in Medical Computer Vision -- A Contemplative Retrospection](https://mlsanity.com/paper/2203.15269/) (2022)
- [A Tunable Loss Function for Binary Classification](https://mlsanity.com/paper/1902.04639/) (2019)
- [Applications of shapelet transform to time series classification of earthquake, wind and wave data](https://mlsanity.com/paper/2004.11243/) (2020)

## Built on by (most cited first, 1 of 1)

- [Rethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning](https://mlsanity.com/paper/2608.19966/) (2026)

## Abstract (arXiv)

Representation learning plays a critical role in the analysis of time series data and has high practical value across a wide range of applications. including trend analysis, time series data retrieval and forecasting. In practice, data confusion is a significant issue as it can considerably impact the effectiveness and accuracy of data analysis, machine learning models and decision-making processes. In general, previous studies did not consider the variability at various levels of granularity, thus resulting in inadequate information utilization, which further exacerbated the issue of data confusion. This paper proposes an unsupervised framework to realize multi-granularity representation learning for time series. Specifically, we employed a cross-granularity transformer to develop an association between fine- and coarse-grained representations. In addition, we introduced a retrieval task as an unsupervised training task to learn the multi-granularity representation of time series. Moreover, a novel loss function was designed to obtain the comprehensive multi-granularity representation of the time series via unsupervised learning. The experimental results revealed that the proposed framework demonstrates significant advantages over alternative representation learning models.