Comparing Kolmogorov-Arnold Network Autoencoders versus MLP Autoencoders for the analysis of biomedical data

Kolmogorov–Arnold Networks (KANs) extend classical neural architectures by replacing fixed activation functions with learnable univariate transformations on network edges, yielding a function-theoretic alternative to Multi-Layer Perceptrons. To evaluate their suitability for unsupervised biomedical signal modelling, we compare fully connected and convolutional autoencoders with parameter-matched Kolmogorov–Arnold counterparts across reconstruction, denoising and inpainting tasks using stethoscope-derived cardiologic signals from the AbnormalHeartbeat dataset. Convolutional variants substantially outperform dense architectures, reflecting the importance of local receptive fields in capturing temporal structure. Within this class, KAN-based convolutional autoencoders (KCAE, KCAE-PS) consistently achieve the lowest test MSE and exhibit superior robustness to noise and missing segments while maintaining reduced parameter counts. PixelShuffle-enhanced KAN models provide the most favourable accuracy–efficiency trade-off, although KAN layers introduce significant computational overhead due to the cost of spline-based functional evaluations. These results demonstrate that Kolmogorov–Arnold parametrisations can enhance the expressive capacity and compactness of convolutional autoencoders for biomedical time-series analysis, while also delineating current performance bottlenecks for large-scale or real-time deployment. • First systematic comparison of neural and Kolmogorov autoencoders on biosignals. • Benchmarked on reconstruction, inpainting, and denoising across key metrics. • Kolmogorov AEs outperform in loss-efficiency but train/test slower due to libraries. • Kolmogorov convolutional AEs with pixel-shuffle decoding outperform all models.