激活空间可选择的Kolmogorov-Arnold网络
Activation Space Selectable Kolmogorov-Arnold Networks
AI总结：
针对单一激活空间导致KAN跨任务性能下降的问题，提出激活空间可选择的S-KAN及S-ConvKAN，在函数拟合和图像分类任务上表现优异，为KAN架构创新提供参考。
摘要：
多层感知机（MLP）是当前人工智能领域的基础范式，广泛应用于计算机视觉、自然语言处理等领域。然而，近期提出的基于非线性加性连接的Kolmogorov-Arnold网络（KAN）已被证明能用显著更少的参数达到与MLP相当的性能。尽管具备这种潜力，单一激活函数空间的使用导致KAN及相关工作在不同任务上性能下降。为解决该问题，我们提出激活空间可选择KAN（S-KAN）。S-KAN采用自适应策略，为每个前馈KAN节点中的数据选择可行的激活模式。我们的方法在7项代表性函数拟合任务中优于基线方法，且显著超越同参数量级的MLP方法。此外，我们扩展了S-KAN的结构，提出激活空间可选择的卷积KAN（S-ConvKAN），在4个通用图像分类数据集上取得了领先结果。我们的方法缓解了原始KAN在不同任务间的性能波动，并通过大量实验证明，具备可选择激活的前馈KAN能够达到甚至超越基于MLP的方法的性能。该工作有助于理解新型AI范式的以数据为中心的设计，为基于KAN的网络架构创新提供了基础参考。
英文摘要：
The multilayer perceptron (MLP), a fundamental paradigm in current artificial intelligence, is widely applied in fields such as computer vision and natural language processing. However, the recently proposed Kolmogorov-Arnold Network (KAN), based on nonlinear additive connections, has been proven to achieve performance comparable to MLPs with significantly fewer parameters. Despite this potential, the use of a single activation function space results in reduced performance of KAN and related works across different tasks. To address this issue, we propose an activation space Selectable KAN (S-KAN). S-KAN employs an adaptive strategy to choose the possible activation mode for data at each feedforward KAN node. Our approach outperforms baseline methods in seven representative function fitting tasks and significantly surpasses MLP methods with the same level of parameters. Furthermore, we extend the structure of S-KAN and propose an activation space selectable Convolutional KAN (S-ConvKAN), which achieves leading results on four general image classification datasets. Our method mitigates the performance variability of the original KAN across different tasks and demonstrates through extensive experiments that feedforward KANs with selectable activations can achieve or even exceed the performance of MLP-based methods. This work contributes to the understanding of the data-centric design of new AI paradigms and provides a foundational reference for innovations in KAN-based network architectures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
