Saved in:
Bibliographic Details
Main Authors: Zhang, Huanyu, Xu, Chang, Zhang, Yi-Fan, Zhang, Zhang, Wang, Liang, Bian, Jiang, Tan, Tieniu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.20810
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913629256810496
author Zhang, Huanyu
Xu, Chang
Zhang, Yi-Fan
Zhang, Zhang
Wang, Liang
Bian, Jiang
Tan, Tieniu
author_facet Zhang, Huanyu
Xu, Chang
Zhang, Yi-Fan
Zhang, Zhang
Wang, Liang
Bian, Jiang
Tan, Tieniu
contents Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation models (TSFMs) have exhibited remarkable generalization capabilities, such as zero-shot learning, through large-scale pre-training. Meanwhile, Retrieval-Augmented Generation (RAG) methods have been widely employed to enhance the performance of foundation models on unseen data, allowing models to access to external knowledge. In this paper, we introduce TimeRAF, a Retrieval-Augmented Forecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques. We develop customized time series knowledge bases that are tailored to the specific forecasting tasks. TimeRAF employs an end-to-end learnable retriever to extract valuable information from the knowledge base. Additionally, we propose Channel Prompting for knowledge integration, which effectively extracts relevant information from the retrieved knowledge along the channel dimension. Extensive experiments demonstrate the effectiveness of our model, showing significant improvement across various domains and datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20810
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting
Zhang, Huanyu
Xu, Chang
Zhang, Yi-Fan
Zhang, Zhang
Wang, Liang
Bian, Jiang
Tan, Tieniu
Machine Learning
Time series forecasting plays a crucial role in data mining, driving rapid advancements across numerous industries. With the emergence of large models, time series foundation models (TSFMs) have exhibited remarkable generalization capabilities, such as zero-shot learning, through large-scale pre-training. Meanwhile, Retrieval-Augmented Generation (RAG) methods have been widely employed to enhance the performance of foundation models on unseen data, allowing models to access to external knowledge. In this paper, we introduce TimeRAF, a Retrieval-Augmented Forecasting model that enhance zero-shot time series forecasting through retrieval-augmented techniques. We develop customized time series knowledge bases that are tailored to the specific forecasting tasks. TimeRAF employs an end-to-end learnable retriever to extract valuable information from the knowledge base. Additionally, we propose Channel Prompting for knowledge integration, which effectively extracts relevant information from the retrieved knowledge along the channel dimension. Extensive experiments demonstrate the effectiveness of our model, showing significant improvement across various domains and datasets.
title TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2412.20810