A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting

Remi Genet, Hugo Inzirillo
6/4/2024
cs.LG

No official code found. Best implementation: remigenet/TKAT (88 stars, JAX, last commit 2024-12-27).

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.

View on arXivView PDF

Code Implementations(1)

remigenet/TKATCommunity100%
JAX

Temporal Kolmogorov-Arnold Transformer

8813Python, Jupyter NotebookJun 3, 20241 years agoNOASSERTION
jaxkeraskeras3temporal-networkstensorflow+6 more

Similar Papers

Sentinel: Multi-Patch Transformer with Temporal and Channel Attention for Time Series Forecasting

88% match2025

Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting

87% match2026

Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability

87% match2024

MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

87% match1 repo2472023

UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting

86% match2024

sTransformer: A Modular Approach for Extracting Inter-Sequential and Temporal Information for Time-Series Forecasting

86% match2024

Cite this paper

@article{genet2024temporal,
  title  = {A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting},
  author = {Remi Genet and Hugo Inzirillo},
  year   = {2024},
  eprint = {2406.02486},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.02486v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.02486.svg)](https://codeofpaper.com/paper/2406.02486)

Discussion