Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Minhua, Chen, Zhengzhang, Liu, Yanchi, Zhao, Xujiang, Wu, Zongyu, Wang, Junxiang, Zhang, Xiang, Wang, Suhang, Chen, Haifeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916743333543936
author Lin, Minhua
Chen, Zhengzhang
Liu, Yanchi
Zhao, Xujiang
Wu, Zongyu
Wang, Junxiang
Zhang, Xiang
Wang, Suhang
Chen, Haifeng
author_facet Lin, Minhua
Chen, Zhengzhang
Liu, Yanchi
Zhao, Xujiang
Wu, Zongyu
Wang, Junxiang
Zhang, Xiang
Wang, Suhang
Chen, Haifeng
contents Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time series and facilitating downstream tasks; however, obtaining such annotations is challenging, particularly in mission-critical domains. In this paper, we propose TESSA, a multi-agent system designed to automatically generate both general and domain-specific annotations for time series data. TESSA introduces two agents: a general annotation agent and a domain-specific annotation agent. The general agent captures common patterns and knowledge across multiple source domains, leveraging both time-series-wise and text-wise features to generate general annotations. Meanwhile, the domain-specific agent utilizes limited annotations from the target domain to learn domain-specific terminology and generate targeted annotations. Extensive experiments on multiple synthetic and real-world datasets demonstrate that TESSA effectively generates high-quality annotations, outperforming existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17462
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
Lin, Minhua
Chen, Zhengzhang
Liu, Yanchi
Zhao, Xujiang
Wu, Zongyu
Wang, Junxiang
Zhang, Xiang
Wang, Suhang
Chen, Haifeng
Artificial Intelligence
Computation and Language
Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time series and facilitating downstream tasks; however, obtaining such annotations is challenging, particularly in mission-critical domains. In this paper, we propose TESSA, a multi-agent system designed to automatically generate both general and domain-specific annotations for time series data. TESSA introduces two agents: a general annotation agent and a domain-specific annotation agent. The general agent captures common patterns and knowledge across multiple source domains, leveraging both time-series-wise and text-wise features to generate general annotations. Meanwhile, the domain-specific agent utilizes limited annotations from the target domain to learn domain-specific terminology and generate targeted annotations. Extensive experiments on multiple synthetic and real-world datasets demonstrate that TESSA effectively generates high-quality annotations, outperforming existing methods.
title Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2410.17462