This paper does not introduce a novel method. Instead, it offers a fairer and more comprehensive comparison of KAN and MLP models across various tasks, including machine learning, computer vision, audio processing, natural language processing, and symbolic formula representation. Specifically, we control the number of parameters and FLOPs to compare the performance of KAN and MLP. Our main observation is that, except for symbolic formula representation tasks, MLP generally outperforms KAN. We also conduct ablation studies on KAN and find that its advantage in symbolic formula representation mainly stems from its B-spline activation function. When B-spline is applied to MLP, performance in symbolic formula representation significantly improves, surpassing or matching that of KAN. However, in other tasks where MLP already excels over KAN, B-spline does not substantially enhance MLP's performance. Furthermore, we find that KAN's forgetting issue is more severe than that of MLP in a standard class-incremental continual learning setting, which differs from the findings reported in the KAN paper. We hope these results provide insights for future research on KAN and other MLP alternatives. Project link: https://github.com/yu-rp/KANbeFair

翻译：本文并未提出新的方法，而是对 KAN 与 MLP 模型在机器学习、计算机视觉、音频处理、自然语言处理和符号公式表示等多种任务上进行了更公平、更全面的比较。具体而言，我们通过控制参数量和浮点运算量来对比 KAN 与 MLP 的性能。我们的主要观察是：除了符号公式表示任务外，MLP 通常优于 KAN。我们还对 KAN 进行了消融研究，发现其在符号公式表示任务中的优势主要源于其 B 样条激活函数。当将 B 样条应用于 MLP 时，其在符号公式表示任务上的性能显著提升，达到甚至超过了 KAN 的水平。然而，在 MLP 原本就优于 KAN 的其他任务中，B 样条并未显著提升 MLP 的性能。此外，我们发现在标准的类增量持续学习设置中，KAN 的遗忘问题比 MLP 更为严重，这与 KAN 论文中报告的结果不同。我们希望这些发现能为未来关于 KAN 及其他 MLP 替代方案的研究提供参考。项目链接：https://github.com/yu-rp/KANbeFair