Saved in:
Bibliographic Details
Main Authors: Hosseini, Sepidehsadat, Zhai, Mengyao, Hajimirsadegh, Hossein, Tung, Frederick
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.02473
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911778006368256
author Hosseini, Sepidehsadat
Zhai, Mengyao
Hajimirsadegh, Hossein
Tung, Frederick
author_facet Hosseini, Sepidehsadat
Zhai, Mengyao
Hajimirsadegh, Hossein
Tung, Frederick
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2310_02473
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Prompting-based Temporal Domain Generalization
Hosseini, Sepidehsadat
Zhai, Mengyao
Hajimirsadegh, Hossein
Tung, Frederick
Machine Learning
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.
title Prompting-based Temporal Domain Generalization
topic Machine Learning
url https://arxiv.org/abs/2310.02473