Hidformer: Hierarchical dual-tower transformer using multi-scale mergence for long-term time series forecasting

计算机科学 变压器 合并(版本控制) 人工智能 机器学习 电压 物理 量子力学 情报检索
作者
Zhaoran Liu,Yizhi Cao,Hu Xu,Yuxin Huang,Qunshan He,Xinjie Chen,Xiaoyu Tang,Xinggao Liu
出处
期刊:Expert Systems With Applications [Elsevier]
卷期号:239: 122412-122412 被引量:8
标识
DOI:10.1016/j.eswa.2023.122412
摘要

Long-term time series forecasting has received a lot of popularity because of its great practicality. It is also an extremely challenging task since it requires using limited observations to predict values in the long future accurately. Recent works have demonstrated that Transformer has strong potential for this task. However, the permutation-invariant property of the Transformer and some other prominent shortcomings in the current Transformer-based models, such as missing multi-scale local features and information from the frequency domain, significantly limit their performance. To improve the accuracy of the long-term time series forecasting, we propose a Transformer-based model called Hidformer. This model can either learn temporal dynamics from the time domain or discover particular patterns from the frequency domain. We also design a segment-and-merge architecture to provide semantic meanings for the inputs and help the model capture multi-scale local features. Besides, we replace Transformer's multi-head attention with highly-efficient recurrence and linear attention, which gives our model an advantage over other Transformer-based models in terms of computational efficiency. Extensive experiments are conducted on seven real-world benchmarks to verify the effectiveness of Hidformer. The experimental results show that Hidformer achieves 72 top-1 and 69 top-2 scores out of 88 configurations. It dramatically improves the prediction accuracy and outperforms the previous state-of-the-art, proving the superiority of our proposed method.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
HHHH发布了新的文献求助10
刚刚
yuki完成签到,获得积分20
1秒前
1秒前
1秒前
bear应助砍柴少年采纳,获得80
4秒前
土壤情缘发布了新的文献求助10
4秒前
4秒前
乔安发布了新的文献求助10
4秒前
ks应助SR采纳,获得20
5秒前
自觉盼雁完成签到,获得积分10
5秒前
5秒前
伊yan发布了新的文献求助10
7秒前
自觉盼雁发布了新的文献求助10
7秒前
英俊的铭应助不苦采纳,获得10
7秒前
可耐的海豚完成签到 ,获得积分10
8秒前
美好斓发布了新的文献求助30
8秒前
张磊发布了新的文献求助10
8秒前
10秒前
10秒前
fat完成签到,获得积分10
10秒前
11秒前
123发布了新的文献求助10
11秒前
11秒前
去旷野发布了新的文献求助10
11秒前
追寻荔枝发布了新的文献求助10
15秒前
含糊的冰安完成签到,获得积分10
15秒前
悦耳冷松完成签到 ,获得积分10
16秒前
Debrolie发布了新的文献求助10
17秒前
17秒前
18秒前
18秒前
19秒前
19秒前
19秒前
Lucas应助LLC采纳,获得10
20秒前
21秒前
34Kenny发布了新的文献求助10
21秒前
xxy发布了新的文献求助10
22秒前
23秒前
Owen应助HHHH采纳,获得10
23秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Smart but Scattered: The Revolutionary Executive Skills Approach to Helping Kids Reach Their Potential (第二版) 1000
Very-high-order BVD Schemes Using β-variable THINC Method 830
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3248155
求助须知:如何正确求助?哪些是违规求助? 2891468
关于积分的说明 8267679
捐赠科研通 2559577
什么是DOI,文献DOI怎么找? 1388384
科研通“疑难数据库(出版商)”最低求助积分说明 650734
邀请新用户注册赠送积分活动 627687