COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification
Authors:
- Jesus BarredaJBJesus Barreda
- Ashley GomezAGAshley Gomez
- Ruben PugaRPRuben Puga
- Kaixiong ZhouKZKaixiong Zhou
- Li ZhangLZLi Zhang
Preprint
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
- Version 1, 2024-09-15, ArXiv
- Published version: , 3622.
This publication has 7 references indexed in Scilit:
- Technology investigation on time series classification and predictionPeerJ Computer Science, 2022
- Sharpness-Aware Minimization Improves Language Model Generalization2022
- The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advancesData Mining and Knowledge Discovery, 2020
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernelsData Mining and Knowledge Discovery, 2020
- Multivariate LSTM-FCNs for time series classificationNeural Networks, 2019
- Deep learning for time series classification: a reviewData Mining and Knowledge Discovery, 2019
- Time Series Classification With Multivariate Convolutional Neural NetworkIEEE Transactions on Industrial Electronics, 2018