TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting

混合(物理) 系列(地层学) 时间序列 计量经济学 计算机科学 统计物理学 数学 地质学 物理 机器学习 古生物学 量子力学
作者
Shiyu Wang,Haixu Wu,Xiaoming Shi,Tengge Hu,Huakun Luo,Lintao Ma,James Y. Zhang,Jun Zhou
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:89
标识
DOI:10.48550/arxiv.2405.14616
摘要

Time series forecasting is widely used in extensive applications, such as traffic planning and weather forecasting. However, real-world time series usually present intricate temporal variations, making forecasting extremely challenging. Going beyond the mainstream paradigms of plain decomposition and multiperiodicity analysis, we analyze temporal variations in a novel view of multiscale-mixing, which is based on an intuitive but important observation that time series present distinct patterns in different sampling scales. The microscopic and the macroscopic information are reflected in fine and coarse scales respectively, and thereby complex variations can be inherently disentangled. Based on this observation, we propose TimeMixer as a fully MLP-based architecture with Past-Decomposable-Mixing (PDM) and Future-Multipredictor-Mixing (FMM) blocks to take full advantage of disentangled multiscale series in both past extraction and future prediction phases. Concretely, PDM applies the decomposition to multiscale series and further mixes the decomposed seasonal and trend components in fine-to-coarse and coarse-to-fine directions separately, which successively aggregates the microscopic seasonal and macroscopic trend information. FMM further ensembles multiple predictors to utilize complementary forecasting capabilities in multiscale observations. Consequently, TimeMixer is able to achieve consistent state-of-the-art performances in both long-term and short-term forecasting tasks with favorable run-time efficiency.
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
1秒前
Zhen Wang发布了新的文献求助10
1秒前
小v1212发布了新的文献求助10
1秒前
莉莉拉贝发布了新的文献求助10
2秒前
Miyoung发布了新的文献求助30
2秒前
yyyy完成签到,获得积分10
2秒前
2秒前
candy完成签到,获得积分10
2秒前
2秒前
深情安青的应助被研友_ZAyqJZ采纳,获得10
2秒前
小孟发布了新的文献求助10
3秒前
所所的应助被冰糖全茶采纳,获得10
3秒前
SONGYILIU发布了新的文献求助10
3秒前
3秒前
科研通AI6.4的应助被Diane丶凯采纳,获得10
3秒前
4秒前
酷波er的应助被悦Rsh采纳,获得10
4秒前
5秒前
yb完成签到,获得积分10
5秒前
Dawn完成签到,获得积分10
5秒前
如此纠结完成签到,获得积分10
5秒前
5秒前
6秒前
二三发布了新的文献求助10
6秒前
eleven完成签到 ,获得积分10
6秒前
vector完成签到,获得积分10
6秒前
JM_L发布了新的文献求助10
6秒前
6秒前
6秒前
王小磊完成签到,获得积分10
7秒前
LB发布了新的文献求助10
7秒前
8秒前
9秒前
9秒前
9秒前
9秒前
李健的应助被小鱼采纳,获得10
9秒前
cccr02发布了新的文献求助10
10秒前
Dawn发布了新的文献求助10
10秒前
123发布了新的文献求助10
10秒前
高分求助中
(应助此贴封号)通过应助OA文献获取积分 10000
Rosenblum, Global Change Biology 800
The Art of Interactive Teaching 600
Computational Chemical Reaction Engineering: Modeling, Simulation, and Design with MATLAB 600
Organizational Behavior 510
Management and the Arts 510
CLSI C56QG Examples of Hemolyzed, Icteric, and Lipemic/Turbid Samples Quick Guide 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 计算机科学 工程类 纳米技术 内科学 物理 有机化学 化学工程 生物化学 复合材料 光电子学 细胞生物学 心理学 量子力学 催化作用 物理化学 电极
热门帖子
关注 科研通微信公众号,转发送积分 7799781
求助须知:如何正确求助?哪些是违规求助? 9334816
关于积分的说明 20469553
捐赠科研通 7390994
什么是DOI,文献DOI怎么找? 3326207
关于科研通互助平台的介绍 2473161
邀请新用户注册赠送积分活动 2343866