用于多元时间序列预测的图神经网络模型

doi:10.3785/j.issn.1008-973X.2024.12.009

浙江大学学报(工学版)

2024, Vol. 58

Issue (12): 2500-2509 DOI: 10.3785/j.issn.1008-973X.2024.12.009

计算机技术

用于多元时间序列预测的图神经网络模型

张晗(

)

东北财经大学数据科学与人工智能学院，大连辽宁 116025

Graph neural network model for multivariate time series forecasting

Han ZHANG(

)

School of Data Science and Artificial Intelligence, Dongbei University of Finance and Economics, Dalian 116025, China

全文: PDF(2953 KB) HTML

摘要：

现有用于多元时序预测的图神经网络模型大多基于预定义图以静态的方式捕捉时序特征，缺少对于系统动态适应和对时序样本之间潜在动态关系的捕捉. 提出用于多元时序预测的图神经网络模型 (MTSGNN). 该模型在一个图学习模块中，采用数据驱动的方式学习时间序列数据的静态图和动态演化图，以捕捉时序样本之间的复杂关系. 通过图交互模块实现静态图和动态图之间的信息交互，并使用卷积运算提取交互信息中的依赖关系. 利用多层感知机对多元时序进行预测. 实验结果表明，所提模型在6个真实的多元时间序列数据集上的预测效果显著优于当前最先进的方法，并且具有参数量较小、运算速度较快的优点.

关键词： 多元时间序列; 图神经网络; 静态图; 动态图; 图交互

Abstract:

Most of the existing graph neural network models for forecasting multivariate time series capture the time series characteristics in a static way based on predefined graphs, and may be lack of capturing the dynamic adaptation of the system and some potential dynamic relationships between time series samples. A graph neural network model for multivariate time series prediction (MTSGNN) was proposed. In a graph learning module, the static and dynamic evolution graphs of time series data were learned in a data-driven way to capture the complex relationships between time series samples. The information interaction between the static and dynamic graphs was realized by the graph interaction module, and the convolution operation was used to extract the dependency in the interaction information. A multi-layer perceptron was used to forecast the multivariate time series. Experimental results on six real multivariate time series datasets showed that the forecasting effect of the proposed model was significantly better than those of the current state-of-the-art methods, and it had the advantages of small parameter quantity and fast operation speed.

Key words: multivariate time series graph neural network static graph dynamic graph graph interaction

收稿日期: 2023-12-30 出版日期: 2024-11-25

CLC:

TP 393

基金资助: 辽宁省应用基础研究计划资助项目(2023JH2/101600040)；辽宁省教育厅基本科研资助项目(LJKMZ20221598).

作者简介: 张晗（1990—），男，讲师，博士，从事神经网络和表示学习研究. orcid.org/0000-0002-7923-7005. E-mail：hanzhang@dufe.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	张晗

引用本文:

张晗. 用于多元时间序列预测的图神经网络模型[J]. 浙江大学学报(工学版), 2024, 58(12): 2500-2509.

Han ZHANG. Graph neural network model for multivariate time series forecasting. Journal of ZheJiang University (Engineering Science), 2024, 58(12): 2500-2509.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.12.009 或 https://www.zjujournals.com/eng/CN/Y2024/V58/I12/2500

图 1 本研究所提模型MTSGNN的整体框架

表 1 基准数据集的统计量

表 2 多步预测任务中所有模型的实验结果

表 3 单步预测任务中所有模型的实验结果

表 4 Exchange-Rate数据集上4个模型每epoch的训练时间

1	WEI W S. Multivariate time series analysis and applications [M]. New York: John Wiley and Sons, 2018.
2	DU S, LI T, YANG Y, et al Multivariate time series forecasting via attention-based encoder-decoder framework[J]. Neurocomputing, 2020, 388: 269- 279 doi: 10.1016/j.neucom.2019.12.118
3	CIABURRO G, IANNACE G Machine learning-based algorithms to knowledge extraction from time series data: a review[J]. Data, 2021, 6 (6): 55 doi: 10.3390/data6060055
4	BENIDIS K, RANGAPURAM S S, FLUNKERT V, et al Deep learning for time series forecasting: tutorial and literature survey[J]. ACM Computing Surveys, 2022, 55 (6): 1- 36
5	FENG S, XU C, ZUO Y, et al Relation-aware dynamic attributed graph attention network for stocks recommendation[J]. Pattern Recognition, 2022, 121: 108119 doi: 10.1016/j.patcog.2021.108119
6	HASANI R, LECHNER M, AMINI A, et al. Liquid time-constant networks [C]// Proceedings of the AAAI Conference on Artificial Intelligence . [s.l.]: AAAI, 2021(35): 7657–7666.
7	SPADON G, HONG S, BRANDOLI B, et al Pay attention to evolution: time series forecasting with deep graph-evolution learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 44 (9): 5368- 5384
8	SHAO Z, ZHANG Z, WANG F, et al. Pre-training enhanced spatial-temporal graph neural network for multivariate time series forecasting [C]// Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining . Washington DC: ACM, 2022: 1567–1577.
9	WU Z, PAN S, LONG G, et al. Connecting the dots: multivariate time series forecasting with graph neural networks [C]/ / Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York: ACM, 2020: 753–763.
10	LI Z L, ZHANG G W, YU J, et al Dynamic graph structure learning for multivariate time series forecasting[J]. Pattern Recognition, 2023, 138: 109423 doi: 10.1016/j.patcog.2023.109423
11	ZHANG D, XIAO F Dynamic auto-structuring graph neural network: a joint learning framework for origin-destination demand prediction[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 35 (4): 3699- 3711
12	ZHANG G P Time series forecasting using a hybrid arima and neural network model[J]. Neurocomputing, 2003, 50: 159- 175 doi: 10.1016/S0925-2312(01)00702-0
13	ROBERTS S, OSBORNE M, EBDEN M, et al Gaussian processes for time-series modelling[J]. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2013, 371 (1984): 20110550 doi: 10.1098/rsta.2011.0550
14	TORRES J F, HADJOUT D, SEBAA A, et al Deep learning for time series forecasting: a survey[J]. Big Data, 2021, 9 (1): 3- 21 doi: 10.1089/big.2020.0159
15	SEN R, YU H F, DHILLON I. Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting [C]// Advances in Neural Information Processing Systems . Vancouver: MIT Press, 2019: 32.
16	SHIH S Y, SUN F K, LEE H Y Temporal pattern attention for multivariate time series forecasting[J]. Machine Learning, 2019, 108: 1421- 1441 doi: 10.1007/s10994-019-05815-0
17	JIN W, MA Y, LIU X, et al. Graph structure learning for robust graph neural networks [C]// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York: ACM, 2020: 66–74.
18	WANG Z, FAN J, WU H, et al Representing multi-view time-series graph structures for multivariate long-term time-series forecasting[J]. IEEE Transactions on Artificial Intelligence, 2024, 5 (6): 2651- 2662
19	TIAN H, ZHENG X, ZHAO K, et al Inductive representation learning on dynamic stock co-movement graphs for stock predictions[J]. INFORMS Journal on Computing, 2022, 34 (4): 1940- 1957 doi: 10.1287/ijoc.2022.1172
20	SRIRAMULU A, FOURRIER N, BERGMEIR C Adaptive dependency learning graph neural networks[J]. Information Sciences, 2023, 625: 700- 714 doi: 10.1016/j.ins.2022.12.086
21	PAREJA A, DOMENICONI G, CHEN J, et al. Evolvegcn: evolving graph convolutional networks for dynamic graphs [C]// Proceedings of the AAAI Conference on Artificial Intelligence . New York: AAAI, 2020(34): 5363–5370.
22	XIE Y, ZHANG Y, GONG M, et al Mgat: multi-view graph attention networks[J]. Neural Networks, 2020, 132: 180- 189 doi: 10.1016/j.neunet.2020.08.021
23	HSU Y L, TSAI Y C, LI C T Fingat: financial graph attention networks for recommending top-k profitable stocks[J]. IEEE Transactions on Knowledge and Data Engineering, 2021, 35 (1): 469- 481
24	VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks [C]// International Conference on Learning Representations . Kigali: ICLR, 2018.
25	CHEN Y, SEGOVIA I, GEL Y R. Z-gcnets: time zigzags at graph convolutional networks for time series forecasting [C]// International Conference on Machine Learning . [s.l.]: PMLR, 2021: 1684–1694.
26	SKARDING J, GABRYS B, MUSIAL K Foundations and modeling of dynamic networks using dynamic graph neural networks: a survey[J]. IEEE Access, 2021, 9: 7914- 79168
27	YU Y, SI X, HU C, et al A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Computation, 2019, 31 (7): 1235- 1270 doi: 10.1162/neco_a_01199
28	BAI L, YAO L, LI C, et al. Adaptive graph convolutional recurrent network for traffic forecasting [C]// Advances in Neural Information Processing Systems . [s.l.]: MIT Press, 2020, 33: 17804–17815.
29	CAO D, WANG Y, DUAN J, et al. Spectral temporal graph neural network for multivariate time-series forecasting [C]// Advances in Neural Information Processing Systems . [s.l.]: MIT Press, 2020, 33: 17766–17778.
30	LIU Y, YANG L, YOU K, et al Graph learning based on spatiotemporal smoothness for time-varying graph signal[J]. IEEE Access, 2019, 7: 62372- 62386 doi: 10.1109/ACCESS.2019.2916567
31	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Advances in Neural Information Processing Systems . Long Beach: MIT Press, 2017: 30.
32	WU Z, PAN S, LONG G, et al. Graph wavenet for deep spatial-temporal graph modeling [C]// Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence . Macao: Morgan Kaufmann, 2019: 1907–1913.
33	LI Y, YU R, SHAHABI C, et al. Diffusion convolutional recurrent neural network: data-driven traffic forecasting [C]// International Conference on Learning Representations . Vancouver: ICLR, 2018.
34	LAI G, CHANG W C, YANG Y, et al. Modeling long-and short-term temporal patterns with deep neural networks [C]// The 41st International ACM SIGIR Conference on Research and Development in Information Retrieval . Ann Arbor: ACM, 2018: 95–104.
35	ZIVOT E, WANG J. Vector autoregressive models for multivariate time series [M]// Modeling financial time series with S-PLUS ® . Berlin: Springer, 2006: 385–429.
36	HUANG S, WANG D, WU X, et al. Dsanet: dual self-attention network for multivariate time series forecasting [C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management . Beijing: ACM, 2019: 2129–2132.
37	YU B, YIN H, ZHU Z. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting [C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence . Stockholm: Morgan Kaufmann, 2018: 3634–3640.
38	GUO S, LIN Y, FENG N, et al. Attention based spatialtemporal graph convolutional networks for traffic flow forecasting [C]// Proceedings of the AAAI Conference on Artificial Intelligence . Honolulu: AAAI, 2019(33): 922–929.
39	SONG C, LIN Y, GUO S, et al. Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting [C]// Proceedings of the AAAI Conference on Artificial Intelligence . New York: AAAI, 2020(34): 914–921.
40	RASUL K, SEWARD C, SCHUSTER I, et al. Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting [C]// International Conference on Machine Learning . [s.l.]: PMLR, 2021: 8857–8868.

[1]	刘议丹,朱小飞,尹雅博. 基于异质图卷积神经网络的论点对抽取模型[J]. 浙江大学学报(工学版), 2024, 58(5): 900-907.
[2]	姚鑫骅,于涛,封森文,马梓健,栾丛丛,沈洪垚. 基于图神经网络的零件机加工特征识别方法[J]. 浙江大学学报(工学版), 2024, 58(2): 349-359.
[3]	周青松,蔡晓东,刘家良. 结合社交影响和长短期偏好的个性化推荐算法[J]. 浙江大学学报(工学版), 2023, 57(3): 495-502.
[4]	曾菊香,王平辉,丁益东,兰林,蔡林熹,管晓宏. 面向节点分类的图神经网络节点嵌入增强模型[J]. 浙江大学学报(工学版), 2023, 57(2): 219-225.
[5]	张京京,张兆功,许鑫. 融合图增强和采样策略的图卷积协同过滤模型[J]. 浙江大学学报(工学版), 2023, 57(2): 243-251.
[6]	周天琪,杨艳,张继杰,殷少伟,郭增强. 基于无负样本损失和自适应增强的图对比学习[J]. 浙江大学学报(工学版), 2023, 57(2): 259-266.
[7]	陆佳炜,李端倪,王策策,徐俊,肖刚. 基于超图卷积神经网络的多行为感知服务推荐方法[J]. 浙江大学学报(工学版), 2023, 57(10): 1977-1986.
[8]	钟帆,柏正尧. 采用动态残差图卷积的3D点云超分辨率[J]. 浙江大学学报(工学版), 2022, 56(11): 2251-2259.
[9]	许佳辉,王敬昌,陈岭,吴勇. 基于图神经网络的地表水水质预测模型[J]. 浙江大学学报(工学版), 2021, 55(4): 601-607.

Viewed

Full text

Abstract

Cited

Shared

Discussed