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.
Bibtex
@misc{hosseini2024promptingbasedtemporaldomaingeneralization,
title={Prompting-based Temporal Domain Generalization},
author={Sepidehsadat Hosseini and Mengyao Zhai and Hossein Hajimirsadegh and Frederick Tung},
year={2024},
eprint={2310.02473},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2310.02473},
}
Related Research
-
Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting
H. R. Medeiros, H. Sharifi, G. Oliveira, and S. Irandoust. Workshop at International Conference on Machine Learning (ICML)
Publications
-
TabReason: A Reinforcement Learning-Enhanced LLM for Accurate and Explainable Tabular Data Prediction
TabReason: A Reinforcement Learning-Enhanced LLM for Accurate and Explainable Tabular Data Prediction
*T. Xu, *Z. Zhang, *X. Sun, *L. K. Zung, *H. Hajimirsadeghi, and G. Mori. Workshop at International Conference on Machine Learning (ICML)
Publications
-
Robustness of LLM-Initialized Bandits for Recommendation Under Noisy Priors
Robustness of LLM-Initialized Bandits for Recommendation Under Noisy Priors
A. Bailey, K. Wilson, Y. Cao, R. Aoki, and X. Zhu. Workshop at 31st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Publications