KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

论文概要

研究领域: cs.AI, eess.SP 作者: Mengxi Liu, Sizhen Bian, Vitor Fortes 发布时间: 2026-05-21 arXiv: 2505.01255

中文摘要

Kolmogorov-Arnold网络（KANs）在干净、低维数据上学习复杂函数方面展现了卓越能力，但在嘈杂且不完美的真实世界数据集上难以保持性能。相比之下，传统的多层感知器（MLPs）对噪声更具容忍性且计算效率更高。在HAR模型中将所有MLP组件替换为KANs往往会降低准确性和计算效率，这突显了一个开放挑战：如何结合KANs的精度与MLPs的噪声鲁棒性和效率。为解决此问题，我们系统地探索了KAN模块在深度HAR网络中的各种放置位置，并提出了一种混合架构，策略性地协同两种范式的优势，它使用基于KAN的输入嵌入层，保留MLP层用于中间特征混合，并引入专门的LarctanKAN模块用于最终活动分类。在八个公共HAR数据集上，混合KAN-MLP模型相比纯MLP模型实现了平均宏F1分数相对提升5.33%，显著优于独立的KAN和MLP基线。此外，将此混合策略整合到其他最先进的HAR架构中持续提升其性能。我们的发现表明，精心协调的KAN、MLP或其他传统神经组件的组合，为真实世界可穿戴传感环境产生了更鲁棒和准确的HAR模型。

原文摘要

Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance on noisy and imperfect real-world datasets. In contrast, conventional multi-layer perceptrons (MLPs) are far more tolerant to noise and computationally efficient. Replacing all MLP components with KANs in HAR models often degrades accuracy and computation efficiency, highlighting an open challenge: how to combine KANs' precision with MLPs' noise robustness and efficiency. To address this, we systematically explore various placements of KAN modules within deep HAR networks and propose a hybrid architecture that strategically synergizes the strengths of both paradigms, which uses a KAN-based input embedding layer, retains MLP layers for intermediate feature mixing, and introduces a specialized LarctanKAN module for final activity classification. Across eight public HAR datasets, the hybrid KAN-MLP model achieves an average macro F1 score relative improvement of 5.33% compared pure-MLP model, significantly outperforming standalone KAN and MLP baselines. Furthermore, integrating this hybrid strategy into other state-of-the-art HAR architectures consistently boosts their performance. Our findings demonstrate that a carefully orchestrated combination of KAN, MLP, or other conventional neural components yields more robust and accurate HAR models for real-world wearable sensing environments.

自动采集于 2026-05-21

#论文 #arXiv #AI #小凯