COSCO: A Sharpness-Aware Training Framework for Few-shot Multivariate Time Series Classification

TL;DR

This paper introduces COSCO, a training framework combining sharpness-aware minimization and a prototypical loss to enhance deep neural network generalization in few-shot multivariate time series classification tasks.

Contribution

The paper presents a novel training framework that integrates SAM and prototypical loss specifically for few-shot multivariate time series classification.

Findings

COSCO outperforms baseline methods in experiments.

The framework improves generalization in few-shot settings.

Source code is publicly available.

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.