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.

翻译：Kolmogorov Arnold Networks (KANs) 是神经计算领域近期的架构进展，为标准的神经网络提供了一个数学基础坚实的替代方案。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，KANs 能够在不采用任何重采样策略的情况下，比多层感知机 (MLPs) 更有效地在原始不平衡数据上取得良好性能。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。至关重要的是，KANs 的计算成本高昂，却没有带来相应的性能提升。统计验证证实，采用不平衡处理技术的 MLPs 能以极低的资源成本，在性能上达到与 KANs 的等效性（各项指标上 |d| < 0.08）。这些发现表明，KANs 代表了一种针对原始不平衡数据的专用解决方案，前提是资源允许。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。我们确定了关键的研究重点：为不平衡学习开发 KAN 特有的架构修改、优化计算效率，以及从理论上调和其与数据增强的冲突。这项工作为下一代 KAN 架构在不平衡分类场景中的应用奠定了基础性见解。