SPAILGMay 14, 2024

Kolmogorov-Arnold Networks (KANs) for Time Series Analysis

arXiv:2405.08790v2227 citationsh-index: 72024 IEEE Globecom Workshops (GC Wkshps)
Originality Incremental advance
AI Analysis

It addresses forecasting challenges in domains like satellite traffic, but is incremental as it adapts an existing KAN method to a new application.

This paper tackled time series forecasting by applying Kolmogorov-Arnold Networks (KANs) to a satellite traffic task, resulting in more accurate predictions with fewer parameters compared to Multi-Layer Perceptrons.

This paper introduces a novel application of Kolmogorov-Arnold Networks (KANs) to time series forecasting, leveraging their adaptive activation functions for enhanced predictive modeling. Inspired by the Kolmogorov-Arnold representation theorem, KANs replace traditional linear weights with spline-parametrized univariate functions, allowing them to learn activation patterns dynamically. We demonstrate that KANs outperforms conventional Multi-Layer Perceptrons (MLPs) in a real-world satellite traffic forecasting task, providing more accurate results with considerably fewer number of learnable parameters. We also provide an ablation study of KAN-specific parameters impact on performance. The proposed approach opens new avenues for adaptive forecasting models, emphasizing the potential of KANs as a powerful tool in predictive analytics.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes