A Systematic Evaluation of Domain Adaptation Algorithms On Time Series Data

Unsupervised domain adaptation methods aim to generalize well on unlabeled test data that may have a different (shifted) distribution from the training data. Such methods are typically developed on image data, and their application to time series data is less explored. Existing works on time series domain adaptation suffer from inconsistencies in evaluation schemes, datasets, and base neural network architectures. Moreover, labeled target data are usually employed for model selection, which violates the fundamental assumption of unsupervised domain adaptation. To address these issues, we propose AdaTime, a standard framework to systematically and fairly evaluate different domain adaptation methods on time series data. Specifically, we standardize the base neural network architectures and benchmarking datasets, while also exploring more realistic model selection approaches that can work with no labeled data or few labeled samples. Our evaluation includes adaptations of state-of-the-art visual domain adaptation methods to time series data in addition to recent methods specifically developed for time series data. We conduct extensive experiments to evaluate 10 state-of-the-art methods on 3 representative datasets spanning 15 cross-domain scenarios. Our results suggest that with careful selection of hyper-parameters, visual domain adaptation methods are competitive with methods proposed for time series domain adaptation. In addition, we find that model selection plays a key role and different selection strategies can significantly affect performance. Our work unveils practical insights for applying domain adaptation methods on time series data and builds a solid foundation for future works in the field.