SigKAN: Signature-Weighted Kolmogorov-Arnold Networks for Time Series

2024/06/25 by Hugo Inzirillo, Inzirillo, Hugo, Rémi Genet +1 · 1 citation
Computer Science · Decision Sciences · #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Stock Market Forecasting Methods #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2406.17890

openalex publication_date 2024/06/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

We propose a novel approach that enhances multivariate function approximation using learnable path signatures and Kolmogorov-Arnold networks (KANs). We enhance the learning capabilities of these networks by weighting the values obtained by KANs using learnable path signatures, which capture important geometric features of paths. This combination allows for a more comprehensive and flexible representation of sequential and temporal data. We demonstrate through studies that our SigKANs with learnable path signatures perform better than conventional methods across a range of function approximation challenges. By leveraging path signatures in neural networks, this method offers intriguing opportunities to enhance performance in time series analysis and time series forecasting, among other fields.

Cited by

• VWAP Execution with Signature-Enhanced Transformers: A Multi-Asset Learning Approach

Related

• Kolmogorov-Arnold Networks (KANs) for Time Series Analysis
• Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability
• A Survey on Kolmogorov-Arnold Network
• TKAN: Temporal Kolmogorov-Arnold Networks
• Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust Analysis