Ordinal-Quadruplet: Retrieval of Missing Classes in Ordinal Time Series

TL;DR

This paper introduces an ordinal-quadruplet loss for robust time series classification that effectively predicts missing classes during testing, significantly improving accuracy even with substantial missing data.

Contribution

It presents a novel ordinal-quadruplet loss and testing procedure that enhance time series classification robustness against missing classes.

Findings

Significant accuracy improvement with up to 40% missing classes.

Nearly double the accuracy compared to triplet loss with interpolation.

Effective in real-world multivariate time series data.

Abstract

In this paper, we propose an ordered time series classification framework that is robust against missing classes in the training data, i.e., during testing we can prescribe classes that are missing during training. This framework relies on two main components: (1) our newly proposed ordinal-quadruplet loss, which forces the model to learn latent representation while preserving the ordinal relation among labels, (2) testing procedure, which utilizes the property of latent representation (order preservation). We conduct experiments based on real world multivariate time series data and show the significant improvement in the prediction of missing labels even with 40% of the classes are missing from training. Compared with the well-known triplet loss optimization augmented with interpolation for missing information, in some cases, we nearly double the accuracy.