Kolmogorov Arnold Network Autoencoder in Medicine

TL;DR

This paper benchmarks various autoencoder architectures, including Kolmogorov Arnold Network Autoencoders, on cardiological audio signals to evaluate their effectiveness in tasks like reconstruction and anomaly detection.

Contribution

It introduces a comprehensive comparison of vanilla and Kolmogorov-Arnold autoencoders on medical audio data across multiple tasks, highlighting the potential advantages of KAN-based models.

Findings

KAN autoencoders perform comparably or better with fewer parameters

Kolmogorov-Arnold architectures excel in denoising and anomaly detection

Benchmark results guide future medical signal processing models

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 \textit{AbnormalHeartbeat} that contains audio signals obtained from the stethoscope.