用于不平衡数据的Kolmogorov Arnold网络（KANs）——一项实证视角研究
Kolmogorov Arnold Networks (KANs) for Imbalanced Data -- An Empirical Perspective
AI总结：
本文实证评估了KANs在不平衡分类中的表现，发现其处理原始不平衡数据优于MLPs但与重采样及焦点损失不兼容且计算成本高，并指出未来需开发KAN专用架构以解决性能-资源权衡问题。
摘要：
Kolmogorov Arnold网络（KANs）是神经计算领域最新的架构进展，为标准神经网络提供了一种具有数学基础的替代方案。本研究在类别不平衡分类的背景下，使用十个基准数据集对KANs进行了实证评估。我们观察到，在没有任何重采样策略的情况下，KANs在处理原始不平衡数据方面本质上比多层感知机（MLPs）表现更有效。然而，传统的不平衡处理策略与KANs的数学结构存在根本性冲突，因为重采样和焦点损失（focal loss）的实现会显著降低KANs的性能，而对MLPs仅有边际收益。关键的是，KANs承受着高昂的计算成本，却没有相应的性能提升。统计验证证实，采用不平衡技术的MLPs以极小的资源成本达到了与KANs相当的性能（各指标上|d| < 0.08）。这些发现表明，在资源允许的情况下，KANs是处理原始不平衡数据的一种专门化解决方案。但其严重的性能-资源权衡以及与标准重采样技术的不兼容性，目前限制了其实际部署。我们将关键研究优先事项确定为：开发针对不平衡学习的KAN专用架构修改、优化计算效率，以及从理论上调和其与数据增强之间的冲突。这项工作为不平衡分类场景中的下一代KAN架构奠定了基础性见解。
英文摘要：
Kolmogorov Arnold Networks (KANs) are recent architectural advancement in neural computation that offer a mathematically grounded alternative to standard neural networks. This study presents an empirical evaluation of KANs in context of class imbalanced classification, using ten benchmark datasets. We observe that KANs can inherently perform well on raw imbalanced data more effectively than Multi-Layer Perceptrons (MLPs) without any resampling strategy. However, conventional imbalance strategies fundamentally conflict with KANs mathematical structure as resampling and focal loss implementations significantly degrade KANs performance, while marginally benefiting MLPs. Crucially, KANs suffer from prohibitive computational costs without proportional performance gains. Statistical validation confirms that MLPs with imbalance techniques achieve equivalence with KANs (|d| < 0.08 across metrics) at minimal resource costs. These findings reveal that KANs represent a specialized solution for raw imbalanced data where resources permit. But their severe performance-resource tradeoffs and incompatibility with standard resampling techniques currently limits practical deployment. We identify critical research priorities as developing KAN specific architectural modifications for imbalance learning, optimizing computational efficiency, and theoretical reconciling their conflict with data augmentation. This work establishes foundational insights for next generation KAN architectures in imbalanced classification scenarios.
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。
