A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Data
This provides a domain-specific evaluation for researchers and practitioners using tabular data, but it is incremental as it applies an existing method to new data.
The paper tackled the lack of real-world testing for Kolmogorov-Arnold Networks (KANs) by benchmarking them against Multi-Layer Perceptrons (MLPs) on tabular datasets, finding that KANs achieved superior or comparable accuracy and F1 scores, especially with large datasets, but at higher computational cost.
Kolmogorov-Arnold Networks (KANs) have very recently been introduced into the world of machine learning, quickly capturing the attention of the entire community. However, KANs have mostly been tested for approximating complex functions or processing synthetic data, while a test on real-world tabular datasets is currently lacking. In this paper, we present a benchmarking study comparing KANs and Multi-Layer Perceptrons (MLPs) on tabular datasets. The study evaluates task performance and training times. From the results obtained on the various datasets, KANs demonstrate superior or comparable accuracy and F1 scores, excelling particularly in datasets with numerous instances, suggesting robust handling of complex data. We also highlight that this performance improvement of KANs comes with a higher computational cost when compared to MLPs of comparable sizes.