COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification
Open Access
- 21 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3622-3626
Abstract
Multivariate time series classification is an important task with widespread domains of applications. Recently, deep neural networks (DNN) have achieved state-of-the-art performance in time series classification. However, they often require large expert-labeled training datasets which can be infeasible in practice. In few-shot settings, i.e. only a limited number of samples per class are available in training data, DNNs show a significant drop in testing accuracy and poor generalization ability. In this paper, we propose to address these problems from an optimization and a loss function perspective. Specifically, we propose a new learning framework named COSCO consisting of a sharpness-aware minimization (SAM) optimization and a Prototypical loss function to improve the generalization ability of DNN for multivariate time series classification problems under few-shot setting. Our experiments demonstrate our proposed method outperforms the existing baseline methods. Our source code is available at: https://github.com/JRB9/COSCO.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Towards Similarity-Aware Time-Series Classification2022
- MiniRocket2021
- The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advancesData Mining and Knowledge Discovery, 2020
- Graph Prototypical Networks for Few-shot Learning on Attributed Networks2020
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernelsData Mining and Knowledge Discovery, 2020
- TapNet: Multivariate Time Series Classification with Attentional Prototypical NetworkProceedings of the AAAI Conference on Artificial Intelligence, 2020
- The UCR time series archiveIEEE/CAA Journal of Automatica Sinica, 2019
- Time Series Classification With Multivariate Convolutional Neural NetworkIEEE Transactions on Industrial Electronics, 2018
- Deep Residual Learning for Image Recognition2016
- Semi-supervised time series classification2006