用纠错码提升KAN在医疗图像分类中的泛化能力
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
- 将多分类转为多个二分类任务，利用汉明距离解码增强鲁棒性
- 在血细胞分类数据集上超越原始KAN，多种超参数下均更准确
- 首次将纠错码引入KAN，适合医疗影像等高可靠性场景
Kolmogorov-Arnold网络（KAN）通过单变量样条组合实现通用函数逼近，无需非线性激活。本文将纠错输出码（ECOC）融入KAN框架，将多分类问题转化为多个二分类任务，通过汉明距离解码提升鲁棒性。所提出的KAN-ECOC框架在具有挑战性的血细胞分类数据集上优于原始KAN，且在多种超参数设置下均表现更优。消融实验进一步验证，ECOC在FastKAN和FasterKAN变体中均能持续提升性能。结果表明，集成ECOC显著增强了KAN在关键医疗AI应用中的泛化能力。据我们所知，这是首个将ECOC与KAN结合以提升多分类医疗图像识别性能的工作。
原文摘要 · Abstract (English)
Kolmogorov-Arnold Networks (KAN) offer universal function approximation using univariate spline compositions without nonlinear activations. In this work, we integrate Error-Correcting Output Codes (ECOC) into the KAN framework to transform multi-class classification into multiple binary tasks, improving robustness via Hamming distance decoding. Our proposed KAN with ECOC framework outperforms vanilla KAN on a challenging blood cell classification dataset, achieving higher accuracy across diverse hyperparameter settings. Ablation studies further confirm that ECOC consistently enhances performance across FastKAN and FasterKAN variants. These results demonstrate that ECOC integration significantly boosts KAN generalizability in critical healthcare AI applications. To the best of our knowledge, this is the first work of ECOC with KAN for enhancing multi-class medical image classification performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。