DP-KAN: Differentially Private Kolmogorov-Arnold Networks
Not on the map. Why?
Abstract (arXiv)
We study the Kolmogorov-Arnold Network (KAN), recently proposed as an alternative to the classical Multilayer Perceptron (MLP), in the application for differentially private model training. Using the DP-SGD algorithm, we demonstrate that KAN can be made private in a straightforward manner and evaluated its performance across several datasets. Our results indicate that the accuracy of KAN is not only comparable with MLP but also experiences similar deterioration due to privacy constraints, making it suitable for differentially private model training.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 14 references that are in the map. First posted on arXiv 17 Jul 2024.
Builds on
10 of 14 references.
References · 10
- 2016Deep Learning with Differential Privacycited by 2,728
- 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 122
- 2024A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networkscited by 104
- 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 98
- 2024Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformationcited by 42
- 2020Differentially Private Simple Linear Regressioncited by 34
- 2024Suitability of KANs for Computer Vision: A preliminary investigationcited by 34
- 2023DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)cited by 28
- 2024A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Datacited by 25
- 2022Easy Differentially Private Linear Regressioncited by 19
Built on by
Not cited yet.