arXiv 2408.113062025-02-11cs.LGcs.AI

KANs在多变量时间序列预测中是否有效？

Are KANs Effective for Multivariate Time Series Forecasting?

School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Pengcheng Laboratory（鹏城实验室）

Xiao Han, Xinfeng Zhang, Yiling Wu, Zhenduo Zhang, Zhe Wu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有多变量时间序列预测方法可解释性不足的问题，本文提出多层KAN混合网络（MMK），从多维度评估KAN有效性，实验表明其在七个数据集上性能优异且保留可解释性。

摘要：

多变量时间序列预测是基于历史输入预测未来状态的关键任务。相关技术随机器学习社区并行发展，从早期的统计学习方法到当前的深度学习方法。尽管取得显著进步，现有方法仍面临可解释性不足的挑战。Kolmogorov-Arnold网络（KAN，科尔莫戈罗夫-阿诺德网络）的兴起为解决这一挑战提供了新视角，但现有研究尚未明确KAN在时间序列预测任务中是否有效。本文旨在从性能、可集成性、效率和可解释性四个维度评估KAN在时间序列预测中的有效性。为此，我们提出多层KAN混合网络（MMK），该网络在保留KAN可转化为符号函数组合能力的同时实现了优异性能。MMK的核心模块是KAN混合层，它采用专家混合结构将变量分配给最匹配的KAN专家。随后，我们探索了一些实用的实验策略来解决训练阶段的问题。最后，我们在七个数据集上比较了MMK与多种基线模型。大量实验和可视化结果表明，KAN在多变量时间序列预测中是有效的。代码可在https://github.com/2448845600/EasyTSF获取。

英文摘要：

Multivariate time series forecasting is a crucial task that predicts the future states based on historical inputs. Related techniques have been developing in parallel with the machine learning community, from early statistical learning methods to current deep learning methods. Despite their significant advancements, existing methods continue to struggle with the challenge of inadequate interpretability. The rise of the Kolmogorov-Arnold Network (KAN) provides a new perspective to solve this challenge, but current work has not yet concluded whether KAN is effective in time series forecasting tasks. In this paper, we aim to evaluate the effectiveness of KANs in time-series forecasting from the perspectives of performance, integrability, efficiency, and interpretability. To this end, we propose the Multi-layer Mixture-of-KAN network (MMK), which achieves excellent performance while retaining KAN's ability to be transformed into a combination of symbolic functions. The core module of MMK is the mixture-of-KAN layer, which uses a mixture-of-experts structure to assign variables to best-matched KAN experts. Then, we explore some useful experimental strategies to deal with the issues in the training stage. Finally, we compare MMK and various baselines on seven datasets. Extensive experimental and visualization results demonstrate that KANs are effective in multivariate time series forecasting. Code is available at: https://github.com/2448845600/EasyTSF.

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。