用柯尔莫哥洛夫网络设计新分类器，缓解持续学习中的遗忘问题。
KAC: Kolmogorov-Arnold Classifier for Continual Learning
- 用KAN的样条函数替代线性分类器，稳定分类空间。
- 在多个基准上提升性能，证明方法有效且鲁棒。
- 适合研究持续学习、模型稳定性与新型分类结构的人参考。
持续学习要求模型在连续任务中不断训练而不遗忘。现有方法多采用线性分类器，难以在学习新任务时保持稳定的分类空间。受柯尔莫哥洛夫-阿诺德网络（KAN）在简单持续回归任务中保持学习稳定性的启发，本文提出一种基于KAN结构的新型分类器——柯尔莫哥洛夫-阿诺德分类器（KAC）。我们研究了KAN中样条函数的影响，并引入径向基函数（RBF）以增强其与持续学习的兼容性。将KAC替换多个近期方法中的线性分类器，在多个持续学习基准上进行实验，均显示性能提升，验证了KAC在持续学习中的有效性与鲁棒性。代码已开源。
原文摘要 · Abstract (English)
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 at https://github.com/Ethanhuhuhu/KAC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。