arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.04853cs.LGcs.AIstat.ML
收藏

TimeCNN:在时间点上优化跨变量交互以用于时间序列预测

TimeCNN: Refining Cross-Variable Interaction on Time Point for Time Series Forecasting

School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics(西南财经大学计算机与人工智能学院);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));HiThink Research, Hithink RoyalFlush Information Network Co., Ltd.(同花顺信息网络有限公司慧研研究院)

Ao Hu, Dongkai Wang, Yong Dai, Shiyi Qi, Liangjian Wen, Jun Wang, Zhi Chen, Xun Zhou, Zenglin Xu, Jiang Duan

AI总结:

针对现有Transformer模型难以捕捉多变量时间序列多面且动态的跨变量相关性的问题,提出时间点独立的TimeCNN模型,在12个数据集上性能优于SOTA,且计算量、参数量显著降低,推理速度达iTransformer的3-4倍。

摘要:

时间序列预测在众多领域中得到广泛应用。基于Transformer的模型在建模跨时间与跨变量交互方面展现出巨大潜力。然而,我们注意到多变量时间序列的跨变量相关性呈现出多面性(正相关与负相关),且会随时间动态变化,现有基于Transformer的模型未能很好地捕捉这一特性。为解决该问题,我们提出TimeCNN模型,通过优化跨变量交互来提升时间序列预测效果。其核心创新点在于时间点独立性:每个时间点都拥有独立的卷积核,使得每个时间点都有专属模型来捕捉变量间的关系。该方法可有效处理正负相关关系,并能适应变量关系随时间演变的特性。我们在12个真实世界数据集上开展了大量实验,结果表明TimeCNN的性能始终优于现有最优模型。值得注意的是,我们的模型大幅降低了计算需求(约60.46%)与参数量(约57.50%),推理速度是基准模型iTransformer的3至4倍。

英文摘要:

Time series forecasting is extensively applied across diverse domains. Transformer-based models demonstrate significant potential in modeling cross-time and cross-variable interaction. However, we notice that the cross-variable correlation of multivariate time series demonstrates multifaceted (positive and negative correlations) and dynamic progression over time, which is not well captured by existing Transformer-based models. To address this issue, we propose a TimeCNN model to refine cross-variable interactions to enhance time series forecasting. Its key innovation is timepoint-independent, where each time point has an independent convolution kernel, allowing each time point to have its independent model to capture relationships among variables. This approach effectively handles both positive and negative correlations and adapts to the evolving nature of variable relationships over time. Extensive experiments conducted on 12 real-world datasets demonstrate that TimeCNN consistently outperforms state-of-the-art models. Notably, our model achieves significant reductions in computational requirements (approximately 60.46%) and parameter count (about 57.50%), while delivering inference speeds 3 to 4 times faster than the benchmark iTransformer model

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑