Prompting-based Temporal Domain Generalization

TL;DR

This paper introduces a prompting-based method for temporal domain generalization that efficiently adapts models to temporal shifts without future data, improving robustness across various tasks.

Contribution

It proposes a novel, parameter-efficient prompting approach that captures temporal dynamics for better generalization over time without future data access.

Findings

Effective across classification, regression, and forecasting tasks

Outperforms existing methods in temporal domain adaptation

Code will be publicly available

Abstract

Machine learning traditionally assumes that the training and testing data are distributed independently and identically. However, in many real-world settings, the data distribution can shift over time, leading to poor generalization of trained models in future time periods. This paper presents a novel prompting-based approach to temporal domain generalization that is parameter-efficient, time-efficient, and does not require access to future data during training. Our method adapts a trained model to temporal drift by learning global prompts, domain-specific prompts, and drift-aware prompts that capture underlying temporal dynamics. Experiments on classification, regression, and time series forecasting tasks demonstrate the generality of the proposed approach. The code repository will be publicly shared.