Time Series Domain Adaptation refers to the process of adapting a predictive model trained on data from one domain (or source domain) to make accurate predictions on data from a different domain (or target domain) while accounting for temporal dynamics. In time series analysis, domains refer to different distributions of data over time.

In traditional domain adaptation, the goal is to adapt a model from a source domain to a target domain where the feature distributions might differ but the label distributions remain the same. However, in time series domain adaptation, the challenge is more complex because not only can the feature distributions differ, but also the temporal dynamics and relationships between variables may vary between domains.

Time series domain adaptation is particularly relevant in various domains, including finance, healthcare, climate science, and industrial processes, where predictive models trained on historical data from one source might not perform well when applied to data from a different source due to temporal variations, seasonality, or other factors.


Prompt-based Domain Discrimination for Multi-source Time Series Domain Adaptation

Time series domain adaptation stands as a pivotal and intricate challenge with diverse applications, including but not limited to human activity recognition, sleep stage classification, and machine fault diagnosis. Despite the numerous domain adaptation techniques proposed to tackle this complex problem, their primary focus has been on the common representations of time series data. This concentration might inadvertently lead to the oversight of valuable domain-specific information originating from different source domains. To bridge this gap, we introduce POND, a novel prompt-based deep learning model designed explicitly for multi-source time series domain adaptation. POND is tailored to address significant challenges, notably: 1) The unavailability of a quantitative relationship between meta-data information and time series distributions, and 2) The dearth of exploration into extracting domain specific meta-data information. In this paper, we present an instance-level prompt generator and afidelity loss mechanism to facilitate the faithful learning of meta-data information. Additionally, we propose a domain discrimination technique to discern domain-specific meta-data information from multiple source domains. Our approach involves a simple yet effective meta-learning algorithm to optimize the objective efficiently. Furthermore, we augment the model’s performance by incorporating the Mixture of Expert (MoE) technique. The efficacy and robustness of our proposed POND model are extensively validated through experiments across 50 scenarios encompassing five datasets, which demonstrates that our proposed POND model outperforms the state-of the-art methods by up to 66% on the F1-score.