Kolmogorov Arnold Network Autoencoder in Medicine

2025-07-19

AI Summary

This study systematically evaluates Kolmogorov–Arnold Network-based autoencoders (KAN-AEs) for five core phonocardiogram signal processing tasks: reconstruction, generation, denoising, completion, and anomaly detection. Departing from conventional linear, convolutional, and variational autoencoders, KAN-AE innovates topologically by placing learnable activation functions on network edges rather than nodes. Under comparable or reduced parameter counts, KAN-AE achieves superior or competitive performance against established baselines on the AbnormalHeartbeat dataset across all tasks. Experimental results demonstrate that KAN-AE exhibits enhanced feature representation capacity and generalization ability, significantly improving modeling efficiency for medical audio signals. This work establishes a novel architectural paradigm for lightweight yet highly expressive neural networks in biomedical signal processing.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Deep learning neural networks architectures such Multi Layer Perceptrons (MLP) and Convolutional blocks still play a crucial role in nowadays research advancements. From a topological point of view, these architecture may be represented as graphs in which we learn the functions related to the nodes while fixed edges convey the information from the input to the output. A recent work introduced a new architecture called Kolmogorov Arnold Networks (KAN) that reports how putting learnable activation functions on the edges of the neural network leads to better performances in multiple scenarios. Multiple studies are focusing on optimizing the KAN architecture by adding important features such as dropout regularization, Autoencoders (AE), model benchmarking and last, but not least, the KAN Convolutional Network (KCN) that introduced matrix convolution with KANs learning. This study aims to benchmark multiple versions of vanilla AEs (such as Linear, Convolutional and Variational) against their Kolmogorov-Arnold counterparts that have same or less number of parameters. Using cardiological signals as model input, a total of five different classic AE tasks were studied: reconstruction, generation, denoising, inpainting and anomaly detection. The proposed experiments uses a medical dataset extit{AbnormalHeartbeat} that contains audio signals obtained from the stethoscope.

Problem

• Benchmarking Kolmogorov-Arnold Autoencoders against classic Autoencoders
• Comparing performance in cardiological signal processing tasks
• Evaluating reconstruction, generation, denoising, inpainting, anomaly detection

Innovation

• Kolmogorov Arnold Networks with learnable edges
• Autoencoder variants benchmarked against KANs
• Medical signal tasks using cardiological data