seqKAN: Sequence processing with Kolmogorov-Arnold Networks

TL;DR

seqKAN introduces a new sequence processing architecture based on Kolmogorov-Arnold Networks, demonstrating superior performance and interpretability in physics-inspired tasks compared to existing models.

Contribution

The paper proposes seqKAN, a novel KAN-based architecture for sequence processing that improves upon prior designs in faithfulness and empirical performance.

Findings

seqKAN outperforms previous KAN architectures in physics-based tasks.

seqKAN achieves better results in extrapolation tasks.

seqKAN maintains high transparency and interpretability.

Abstract

Kolmogorov-Arnold Networks (KANs) have been recently proposed as a machine learning framework that is more interpretable and controllable than the multi-layer perceptron. Various network architectures have been proposed within the KAN framework targeting different tasks and application domains, including sequence processing. This paper proposes seqKAN, a new KAN architecture for sequence processing. Although multiple sequence processing KAN architectures have already been proposed, we argue that seqKAN is more faithful to the core concept of the KAN framework. Furthermore, we empirically demonstrate that it achieves better results. The empirical evaluation is performed on generated data from a complex physics problem on an interpolation and an extrapolation task. Using this dataset we compared seqKAN against a prior KAN network for timeseries prediction, recurrent deep networks, and symbolic regression. seqKAN substantially outperforms all architectures, particularly on the extrapolation dataset, while also being the most transparent.