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

• URL: http://arxiv.org/abs/2605.19031v1
• Date: Mon, 18 May 2026 18:55:46 GMT
• Title: KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition
• Abstract summary: Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data.<n>In contrast, conventional multi-layer perceptrons (MLPs) are far more tolerant to noise and computationally efficient.<n> Replacing all components with KANs in HAR models often degrades accuracy and efficiency.<n>We propose a hybrid architecture that strategically synergizes the strengths of both paradigms.
• Score: 11.011155958467787
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Dual-Stream MLP is All You Need for CTR Prediction [81.87859550137382]
  Click-through rate (CTR) prediction holds a pivotal role in online advertising and recommendation systems, where even small improvements can significantly boost revenue.<n>Existing research primarily focuses on designing dual-stream architectures to capture effective complex feature interactions from both explicit and implicit perspectives.<n>These approaches are faced with two major challenges: 1) the high complexity of feature interaction learning, which increases computational demands and the overfitting risk, and 2) the imbalance between explicit and implicit modules, where one module's output may dominate the final prediction.<n>We propose Dual-Stream (DSMLP), a novel feature interaction framework for the CTR prediction task.
  arXiv  Detail & Related papers  (2026-06-03T14:34:32Z)
• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming [52.52020895303244]
  Mixed-Integer Linear Programming (MILP) is a foundational tool for complex decision-making problems.<n>We propose Joint Continuous-Integer Flow for Mixed-Integer Linear Programming (FMIP), which is the first generative framework that models joint distribution of both integer and continuous variables for MILP solutions.<n>FMIP is fully compatible with arbitrary backbone networks and various downstream solvers, making it well-suited for a broad range of real-world MILP applications.
  arXiv  Detail & Related papers  (2025-07-31T10:03:30Z)
• Scientific Machine Learning with Kolmogorov-Arnold Networks [0.0]
  The field of scientific machine learning is increasingly adopting Kolmogorov-Arnold Networks (KANs) for data encoding.<n>KANs address issues with enhanced interpretability and flexibility, enabling more efficient modeling of complex nonlinear interactions.<n>This review categorizes recent progress in KAN-based models across three perspectives: (i) data-driven learning, (ii) physics-informed modeling, and (iii) deep-operator learning.
  arXiv  Detail & Related papers  (2025-07-30T01:26:44Z)
• Bridging KAN and MLP: MJKAN, a Hybrid Architecture with Both Efficiency and Expressiveness [5.474797258314827]
  Modulation Joint KAN (MJKAN) is a novel neural network layer designed to overcome these challenges.<n>MJKAN integrates a FiLM (Feature-wise Linear Modulation)-like mechanism with Radial Basis Function activations.<n>We empirically validated MJKAN's performance across a diverse set of benchmarks, including function regression, image classification (MNIST, CIFAR-10/100), and natural language processing (AG News, SMS)
  arXiv  Detail & Related papers  (2025-07-07T06:13:32Z)
• Enhancing Federated Learning with Kolmogorov-Arnold Networks: A Comparative Study Across Diverse Aggregation Strategies [0.24578723416255752]
  Kolmogorov-Arnold Networks (KAN) have shown promising capabilities in modeling complex nonlinear relationships.<n>KANs consistently outperform Multilayer Perceptrons in terms of accuracy, stability, and convergence efficiency.
  arXiv  Detail & Related papers  (2025-05-12T14:56:27Z)
• KAN-Mixers: a new deep learning architecture for image classification [0.0]
  The present work aims to design a new mixer-based architecture, called KAN-Mixers, using KANs as main layers and evaluate its performance.<n>As main results obtained, the KAN-Mixers model was superior to theNIST-Mixer and KAN models.
  arXiv  Detail & Related papers  (2025-03-11T22:41:22Z)
• Incorporating Arbitrary Matrix Group Equivariance into KANs [69.30866522377694]
  Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains.<n>We propose Equivariant Kolmogorov-Arnold Networks (EKAN) to broaden their applicability to more fields.
  arXiv  Detail & Related papers  (2024-10-01T06:34:58Z)
• Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons [2.77390041716769]
  Kolmogorov-Arnold Networks (KANs) use highly flexible learnable activation functions directly on network edges. KANs significantly increase the number of learnable parameters, raising concerns about their effectiveness in data-scarce environments. We show that individualized activation functions achieve significantly higher predictive accuracy with only a modest increase in parameters.
  arXiv  Detail & Related papers  (2024-09-16T16:56:08Z)
• Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL [57.745700271150454]
  We study the sample complexity of reinforcement learning in Mean-Field Games (MFGs) with model-based function approximation. We introduce the Partial Model-Based Eluder Dimension (P-MBED), a more effective notion to characterize the model class complexity.
  arXiv  Detail & Related papers  (2024-02-08T14:54:47Z)
• Efficient Language Modeling with Sparse all-MLP [53.81435968051093]
  All-MLPs can match Transformers in language modeling, but still lag behind in downstream tasks. We propose sparse all-MLPs with mixture-of-experts (MoEs) in both feature and input (tokens) We evaluate its zero-shot in-context learning performance on six downstream tasks, and find that it surpasses Transformer-based MoEs and dense Transformers.
  arXiv  Detail & Related papers  (2022-03-14T04:32:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.