Preprints, Working Papers, ... Year : 2024

A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting

Abstract

Capturing complex temporal patterns and relationships within multivariate data streams is a difficult task. We propose the Temporal Kolmogorov-Arnold Transformer (TKAT), a novel attention-based architecture designed to address this task using Temporal Kolmogorov-Arnold Networks (TKANs). Inspired by the Temporal Fusion Transformer (TFT), TKAT emerges as a powerful encoder-decoder model tailored to handle tasks in which the observed part of the features is more important than the a priori known part. This new architecture combined the theoretical foundation of the Kolmogorov-Arnold representation with the power of transformers. TKAT aims to simplify the complex dependencies inherent in time series, making them more "interpretable". The use of transformer architecture in this framework allows us to capture long-range dependencies through self-attention mechanisms.

Keywords

Fichier principal
Vignette du fichier
2406.02486v2.pdf (401) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04921924 , version 1 (01-02-2025)

Identifiers

Cite

Rémi Genet, Hugo Inzirillo. A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting. 2025. ⟨hal-04921924⟩
0 View
0 Download

Altmetric

Share

More