Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment
This work addresses domain adaptation for time series data, which is crucial for applications like remote sensing where labeled data is scarce, though it appears incremental as it builds on existing methods like optimal transport and dynamic time warping.
The paper tackles unsupervised domain adaptation for time series by addressing both feature distribution shifts and temporal misalignments, introducing the Match-And-Deform (MAD) approach that combines optimal transport and dynamic time warping to align domains and improve classification, achieving similar or better performance than state-of-the-art methods on benchmark datasets.
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.