Can I read COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification on EtoBox?

COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification by Barreda, Jesus; Gomez, Ashley; Puga, Ruben; Zhou, Kaixiong; Zhang, Li is a scholarly article available to read on EtoBox.

What is COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification about?

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.

Author

Barreda, Jesus; Gomez, Ashley; Puga, Ruben; Zhou, Kaixiong; Zhang, Li

Published

2024

Language

EN