重新构想线性探测：迁移学习中的柯尔莫哥洛夫-阿诺德网络（Kolmogorov-Arnold Networks）
Reimagining Linear Probing: Kolmogorov-Arnold Networks in Transfer Learning
AI总结：
针对传统线性探测无法建模复杂数据关系的问题，提出用基于样条表示的KAN替代预训练模型的线性探测层，在CIFAR-10上验证其准确率和泛化性优于传统线性探测。
摘要：
本文提出将柯尔莫哥洛夫-阿诺德网络（Kolmogorov-Arnold Networks，KAN）作为迁移学习中传统线性探测方法的增强方案。线性探测通常应用于预训练模型的最后一层，其局限性在于无法对数据中的复杂关系建模。为解决这一问题，我们提出用KAN替代线性探测层，KAN利用基于样条的表示来逼近复杂函数。本研究将KAN与在ImageNet上预训练的ResNet-50模型集成，并在CIFAR-10数据集上评估其性能。我们开展了系统的超参数搜索，重点关注网格大小和样条阶数（k），以优化KAN的灵活性和准确率。结果表明，KAN的性能始终优于传统线性探测，在多种配置下均实现了准确率和泛化能力的显著提升。这些发现表明，在迁移学习中，KAN是比传统线性探测技术更强大、适应性更强的替代方案。
英文摘要：
This paper introduces Kolmogorov-Arnold Networks (KAN) as an enhancement to the traditional linear probing method in transfer learning. Linear probing, often applied to the final layer of pre-trained models, is limited by its inability to model complex relationships in data. To address this, we propose substituting the linear probing layer with KAN, which leverages spline-based representations to approximate intricate functions. In this study, we integrate KAN with a ResNet-50 model pre-trained on ImageNet and evaluate its performance on the CIFAR-10 dataset. We perform a systematic hyperparameter search, focusing on grid size and spline degree (k), to optimize KAN's flexibility and accuracy. Our results demonstrate that KAN consistently outperforms traditional linear probing, achieving significant improvements in accuracy and generalization across a range of configurations. These findings indicate that KAN offers a more powerful and adaptable alternative to conventional linear probing techniques in transfer learning.
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。
