基于Shapley值的Kolmogorov-Arnold网络平移不变属性评分
Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value
AI总结：
提出ShapKAN框架，利用Shapley值归因实现平移不变的节点重要性评估，有效压缩KAN网络并保持其可解释性优势。
摘要：
对于许多实际应用，理解特征与结果之间的关系与实现高预测准确性同样重要。虽然传统神经网络在预测方面表现出色，但其黑箱性质掩盖了潜在的功能关系。Kolmogorov-Arnold网络（KAN）通过在边上采用可学习的基于样条的激活函数来解决这一问题，能够在保持竞争性能的同时恢复符号表示。然而，KAN的架构对网络剪枝提出了独特的挑战。由于对输入坐标平移的敏感性，传统的基于幅度的方法变得不可靠。我们提出了\textbf{ShapKAN}，一种使用Shapley值归因以平移不变方式评估节点重要性的剪枝框架。与基于幅度的方法不同，ShapKAN量化每个节点的实际贡献，确保无论输入参数化如何，重要性排名保持一致。在合成和真实世界数据集上的大量实验表明，ShapKAN在实现有效网络压缩的同时保留了真实的节点重要性。我们的方法提升了KAN的可解释性优势，便于在资源受限环境中部署。
英文摘要：
For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at prediction, their black-box nature obscures underlying functional relationships. Kolmogorov--Arnold Networks (KANs) address this by employing learnable spline-based activation functions on edges, enabling recovery of symbolic representations while maintaining competitive performance. However, KAN's architecture presents unique challenges for network pruning. Conventional magnitude-based methods become unreliable due to sensitivity to input coordinate shifts. We propose \textbf{ShapKAN}, a pruning framework using Shapley value attribution to assess node importance in a shift-invariant manner. Unlike magnitude-based approaches, ShapKAN quantifies each node's actual contribution, ensuring consistent importance rankings regardless of input parameterization. Extensive experiments on synthetic and real-world datasets demonstrate that ShapKAN preserves true node importance while enabling effective network compression. Our approach improves KAN's interpretability advantages, facilitating deployment in resource-constrained environments.
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。
