BriefGPT.xyz
Aug, 2023
LLM4TS:基于预训练LLM的两阶段微调用于时间序列预测
LLM4TS: Two-Stage Fine-Tuning for Time-Series Forecasting with Pre-Trained LLMs
HTML
PDF
Ching Chang, Wen-Chih Peng, Tien-Fu Chen
TL;DR
我们利用预训练的大型语言模型 (LLMs) 提升时间序列预测的能力,通过结合时间序列拼接和时间编码,增强了LLMs处理时间序列数据的能力,采用两阶段的精调过程,并采用多种参数高效精调技术 (PEFT),LLM4TS在长期预测方面取得了最先进的结果。
Abstract
In this work, we leverage pre-trained
large language models
(LLMs) to enhance
time-series forecasting
. Mirroring the growing interest in unifying models for Natural Language Processing and Computer Vision, we env
→