CVKAN: Complex-valued Kolmogorov-Arnold Networks

Wolff, Matthias; Eilers, Florian; Jiang, Xiaoyi

Forschungsartikel in Sammelband (Konferenz) | Peer reviewed

Zusammenfassung

In this work we propose CVKAN, a complex-valued KAN, to join the intrinsic interpretability of KANs and the advantages of Complex-Valued Neural Networks (CVNNs). We show how to transfer a KAN and the necessary associated mechanisms into the complex domain. To confirm that CVKAN meets expectations we conduct experiments on symbolic complex-valued function fitting and physically meaningful formulae as well as on a more realistic dataset from knot theory. Our proposed CVKAN is more stable and performs on par or better than real-valued KANs while requiring less parameters and a shallower network architecture, making it more explainable.

Details zur Publikation

BuchtitelProc. of IJCNN
Artikelnummer2502.02417
Statusakzeptiert / in Druck (unveröffentlicht)
Veröffentlichungsjahr2025 (04.02.2025)
Sprache, in der die Publikation verfasst istEnglisch
KonferenzInternational Joint Conference on Neural Networks, Rome, Italien
DOI10.48550/arXiv.2502.02417
Link zum Volltexthttps://arxiv.org/pdf/2502.02417
StichwörterComplex-Valued Neural Networks; Kolmogorov-Arnold Networks; Explainable AI

Autor*innen der Universität Münster

Eilers, Florian
Professur für Praktische Informatik (Prof. Jiang)
Jiang, Xiaoyi
Professur für Praktische Informatik (Prof. Jiang)
Wolff, Matthias Carlo
Professur für Praktische Informatik (Prof. Jiang)