Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks. Inspired by the success of Kolmogorov-Arnold Networks (KAN) in preserving learning stability during simple continual regression tasks, we set out to explore their potential in more complex continual learning scenarios. In this paper, we introduce the Kolmogorov-Arnold Classifier (KAC), a novel classifier developed for continual learning based on the KAN structure. We delve into the impact of KAN's spline functions and introduce Radial Basis Functions (RBF) for improved compatibility with continual learning. We replace linear classifiers with KAC in several recent approaches and conduct experiments across various continual learning benchmarks, all of which demonstrate performance improvements, highlighting the effectiveness and robustness of KAC in continual learning. The code is available atthis https URL.
View on arXiv@article{hu2025_2503.21076,
title={ KAC: Kolmogorov-Arnold Classifier for Continual Learning },
author={ Yusong Hu and Zichen Liang and Fei Yang and Qibin Hou and Xialei Liu and Ming-Ming Cheng },
journal={arXiv preprint arXiv:2503.21076},
year={ 2025 }
}