seqKAN: Sequence processing with Kolmogorov-Arnold Networks
This work addresses sequence processing tasks, offering improved performance and transparency, but it is incremental as it builds on the existing KAN framework.
The paper introduces seqKAN, a new Kolmogorov-Arnold Network architecture for sequence processing, which outperforms prior KAN networks, recurrent deep networks, and symbolic regression on interpolation and extrapolation tasks using a complex physics dataset, particularly excelling in extrapolation.
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.