Are KANs Effective for Multivariate Time Series Forecasting?

2024-08-21

AI Summary

Addressing the challenge of balancing model interpretability and predictive performance in multivariate time series forecasting, this paper systematically evaluates the effectiveness of Kolmogorov–Arnold Networks (KANs) and proposes a novel Multilayer Mixture KAN (MMK). MMK introduces, for the first time, a dynamic variable allocation mechanism that integrates KANs with Mixture-of-Experts (MoE), incorporates symbolic function modeling to enhance interpretability, and enables adaptive temporal feature learning. Extensive experiments across seven standard benchmarks demonstrate that MMK consistently outperforms state-of-the-art baselines in prediction accuracy, inference efficiency, and interpretability. Notably, this work provides the first empirical validation that KAN-based architectures can simultaneously achieve high forecasting performance and strong interpretability in multivariate time series settings. By unifying structural transparency with expressive modeling capacity, MMK establishes a new paradigm for trustworthy time series modeling.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Evaluate KANs in time-series forecasting
• Enhance interpretability of forecasting methods
• Propose Multi-layer Mixture-of-KAN network

Innovation

• Uses Multi-layer Mixture-of-KAN network
• Employs mixture-of-experts structure
• Transforms KAN into symbolic functions