亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

计算机科学 杠杆(统计) 人工智能 背景(考古学) 机器学习 时间序列 系列(地层学) 语言模型 模式 地理 古生物学 社会科学 考古 社会学 生物
作者
Ming Jin,Shiyu Wang,Lintao Ma,Zhixuan Chu,James Y. Zhang,Xiaoming Shi,Pin‐Yu Chen,Yuxuan Liang,Yuan-Fang Li,Shirui Pan,Qingsong Wen
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:127
标识
DOI:10.48550/arxiv.2310.01728
摘要

Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks, models for time series forecasting are often specialized, necessitating distinct designs for different tasks and applications. While pre-trained foundation models have made impressive strides in NLP and CV, their development in time series domains has been constrained by data sparsity. Recent studies have revealed that large language models (LLMs) possess robust pattern recognition and reasoning abilities over complex sequences of tokens. However, the challenge remains in effectively aligning the modalities of time series data and natural language to leverage these capabilities. In this work, we present Time-LLM, a reprogramming framework to repurpose LLMs for general time series forecasting with the backbone language models kept intact. We begin by reprogramming the input time series with text prototypes before feeding it into the frozen LLM to align the two modalities. To augment the LLM's ability to reason with time series data, we propose Prompt-as-Prefix (PaP), which enriches the input context and directs the transformation of reprogrammed input patches. The transformed time series patches from the LLM are finally projected to obtain the forecasts. Our comprehensive evaluations demonstrate that Time-LLM is a powerful time series learner that outperforms state-of-the-art, specialized forecasting models. Moreover, Time-LLM excels in both few-shot and zero-shot learning scenarios.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
光亮的成败完成签到,获得积分10
20秒前
我是老大应助jianglan采纳,获得10
21秒前
35秒前
万能图书馆应助tongluobing采纳,获得10
35秒前
顾矜应助锅包肉采纳,获得30
40秒前
柳贯一发布了新的文献求助10
41秒前
bkagyin应助科研通管家采纳,获得10
49秒前
Wells应助科研通管家采纳,获得10
49秒前
YifanWang应助科研通管家采纳,获得10
49秒前
Wells应助科研通管家采纳,获得10
50秒前
50秒前
殷勤的鸵鸟完成签到,获得积分10
58秒前
大气钧完成签到,获得积分10
1分钟前
然宝应助冷静机器猫采纳,获得30
1分钟前
外向的以莲完成签到,获得积分10
1分钟前
闪闪尔竹完成签到 ,获得积分10
2分钟前
鲜艳的雪曼完成签到,获得积分10
2分钟前
天天天晴完成签到 ,获得积分10
2分钟前
2分钟前
锅包肉发布了新的文献求助30
2分钟前
2分钟前
2分钟前
纯真蓝发布了新的文献求助10
2分钟前
锅包肉完成签到,获得积分10
2分钟前
tiger发布了新的文献求助20
2分钟前
心灵美的思柔完成签到,获得积分10
2分钟前
fantw发布了新的文献求助10
2分钟前
云淡风轻一宝完成签到,获得积分10
2分钟前
深情安青应助纯真蓝采纳,获得10
2分钟前
万能图书馆应助zhoushishan采纳,获得10
2分钟前
科研通AI6.4应助fantw采纳,获得10
2分钟前
傲娇断天完成签到,获得积分10
2分钟前
2分钟前
李健应助科研通管家采纳,获得10
2分钟前
YifanWang应助科研通管家采纳,获得10
2分钟前
纯真蓝完成签到,获得积分10
2分钟前
2分钟前
tiger完成签到,获得积分10
2分钟前
zhoushishan发布了新的文献求助10
2分钟前
复杂以旋完成签到,获得积分10
3分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Principles of town planning: translating concepts to applications 1000
Navigating Normative Orders. Interdisciplinary Perspectives 800
1 Peter and Christ's Descent to the Dead in Its Early Christian Reception 700
Organizational Behavior 510
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7738734
求助须知:如何正确求助?哪些是违规求助? 9287735
关于积分的说明 20184701
捐赠科研通 7316625
什么是DOI,文献DOI怎么找? 3305994
关于科研通互助平台的介绍 2458323
邀请新用户注册赠送积分活动 2315885