# Finding Foundation Models for Time Series Classification with a PreText Task

arXiv: https://arxiv.org/abs/2311.14534 · HTML: https://mlsanity.com/paper/2311.14534/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Builds on (most cited first, 18 of 18)

- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classification](https://mlsanity.com/paper/2012.08791/) (2020)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Bake off redux: a review and experimental evaluation of recent time series classification algorithms](https://mlsanity.com/paper/2304.13029/) (2023)
- [MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification](https://mlsanity.com/paper/2102.00457/) (2021)
- [Transfer learning for time series classification](https://mlsanity.com/paper/1811.01533/) (2018)
- [HYDRA: Competing convolutional kernels for fast and accurate time series classification](https://mlsanity.com/paper/2203.13652/) (2022)
- [Fast and Accurate Time Series Classification with WEASEL](https://mlsanity.com/paper/1701.07681/) (2017)
- [Data augmentation using synthetic data for time series classification with deep residual networks](https://mlsanity.com/paper/1808.02455/) (2018)
- [An Approach to Multiple Comparison Benchmark Evaluations that is Stable Under Manipulation of the Comparate Set](https://mlsanity.com/paper/2305.11921/) (2023)
- [WEASEL 2.0 -- A Random Dilated Dictionary Transform for Fast, Accurate and Memory Constrained Time Series Classification](https://mlsanity.com/paper/2301.10194/) (2023)
- [Unsupervised Feature Based Algorithms for Time Series Extrinsic Regression](https://mlsanity.com/paper/2305.01429/) (2023)
- [ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging](https://mlsanity.com/paper/2309.16353/) (2023)
- [Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data](https://mlsanity.com/paper/2307.03347/) (2023)

## Built on by (most cited first, 4 of 4)

- [Look Into the LITE in Deep Learning for Time Series Classification](https://mlsanity.com/paper/2409.02869/) (2024)
- [On the Feasibility of Vision-Language Models for Time-Series Classification](https://mlsanity.com/paper/2412.17304/) (2024)
- [Establishing a Unified Evaluation Framework for Human Motion Generation: A Comparative Analysis of Metrics](https://mlsanity.com/paper/2405.07680/) (2024)
- [The impact of data set similarity and diversity on transfer learning success in time series forecasting](https://mlsanity.com/paper/2404.06198/) (2024)

## Abstract (arXiv)

Over the past decade, Time Series Classification (TSC) has gained an increasing attention. While various methods were explored, deep learning - particularly through Convolutional Neural Networks (CNNs)-stands out as an effective approach. However, due to the limited availability of training data, defining a foundation model for TSC that overcomes the overfitting problem is still a challenging task. The UCR archive, encompassing a wide spectrum of datasets ranging from motion recognition to ECG-based heart disease detection, serves as a prime example for exploring this issue in diverse TSC scenarios. In this paper, we address the overfitting challenge by introducing pre-trained domain foundation models. A key aspect of our methodology is a novel pretext task that spans multiple datasets. This task is designed to identify the originating dataset of each time series sample, with the goal of creating flexible convolution filters that can be applied across different datasets. The research process consists of two phases: a pre-training phase where the model acquires general features through the pretext task, and a subsequent fine-tuning phase for specific dataset classifications. Our extensive experiments on the UCR archive demonstrate that this pre-training strategy significantly outperforms the conventional training approach without pre-training. This strategy effectively reduces overfitting in small datasets and provides an efficient route for adapting these models to new datasets, thus advancing the capabilities of deep learning in TSC.