一种用于专家混合的门控残差Kolmogorov-Arnold网络
A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Experts
AI总结：
该研究提出基于GRKAN的新型专家混合框架KAMoE，替代传统门控函数以提升效率和可解释性，实验证明其在多类任务中优于传统MoE架构，并分析了模型复杂度与性能的权衡。
摘要：
本文提出KAMoE，这是一种基于门控残差Kolmogorov-Arnold网络（GRKAN）的新型专家混合（MoE）框架。我们提出GRKAN作为传统门控函数的替代方案，旨在提升MoE建模的效率与可解释性。通过在数字资产市场和房地产估值上的大量实验，我们证明KAMoE在各类任务和模型类型中始终优于传统MoE架构。结果显示，GRKAN相比标准门控残差网络表现更优，尤其在基于LSTM的序列任务模型中。我们还分析了MoE和KAMoE架构中模型复杂度与性能增益之间的权衡关系。
英文摘要：
This paper introduces KAMoE, a novel Mixture of Experts (MoE) framework based on Gated Residual Kolmogorov-Arnold Networks (GRKAN). We propose GRKAN as an alternative to the traditional gating function, aiming to enhance efficiency and interpretability in MoE modeling. Through extensive experiments on digital asset markets and real estate valuation, we demonstrate that KAMoE consistently outperforms traditional MoE architectures across various tasks and model types. Our results show that GRKAN exhibits superior performance compared to standard Gating Residual Networks, particularly in LSTM-based models for sequential tasks. We also provide insights into the trade-offs between model complexity and performance gains in MoE and KAMoE architectures.
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。
