Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment

TL;DR

The paper introduces Match-And-Deform (MAD), a novel method for unsupervised domain adaptation in time series data that aligns source and target series using optimal transport and temporal warping, improving classification accuracy.

Contribution

MAD is the first approach to jointly align time series domains with optimal transport and dynamic time warping within a deep learning framework.

Findings

MAD achieves meaningful sample pairing and time shift estimation.

MAD outperforms or matches state-of-the-art methods on benchmark datasets.

MAD enhances domain adaptation for time series classification.

Abstract

While large volumes of unlabeled data are usually available, associated labels are often scarce. The unsupervised domain adaptation problem aims at exploiting labels from a source domain to classify data from a related, yet different, target domain. When time series are at stake, new difficulties arise as temporal shifts may appear in addition to the standard feature distribution shift. In this paper, we introduce the Match-And-Deform (MAD) approach that aims at finding correspondences between the source and target time series while allowing temporal distortions. The associated optimization problem simultaneously aligns the series thanks to an optimal transport loss and the time stamps through dynamic time warping. When embedded into a deep neural network, MAD helps learning new representations of time series that both align the domains and maximize the discriminative power of the network. Empirical studies on benchmark datasets and remote sensing data demonstrate that MAD makes meaningful sample-to-sample pairing and time shift estimation, reaching similar or better classification performance than state-of-the-art deep time series domain adaptation strategies.