Litcius/Paper detail

ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU

Qi Qiu, Tao Zhu, Helin Gong, Liming Chen, Huansheng Ning

20258 citationsDOI

Abstract

The Kolmogorov-Arnold Network (KAN), as a recent and promising alternative to the Multilayer Perceptron (MLP), has garnered significant attention in academia. The B-spline function within KAN plays a crucial role in function approximation. However, the complexity of B-spline function limits the training efficiency of KAN on GPUs, and their inflexibility restricts KAN’s approximation capacity. We propose a novel KAN-like architecture named ReLU-KAN, which replaces the B-spline in KAN with a simpler function R composed solely of matrix addition, dot product, and ReLU activation. This design enables efficient GPU parallelization for faster backpropagation compared to the KAN. Additionally, the R function incorporates two trainable hyperparameters, allowing it to dynamically adapt its shape and capture intricate relationships within the data. This adaptive capability demonstrates a significant accuracy improvement. In the experiment, the new architecture improves 1-3 orders of magnitude compared with the original scheme. Notably, ReLU-KAN retains the original model’s ability to avoid catastrophic forgetting.

Topics & Concepts

Computer scienceFunction (biology)Matrix (chemical analysis)AlgorithmBackpropagationActivation functionArtificial neural networkArchitecturePerceptronFunction approximationArtificial intelligenceNetwork architectureMultilayer perceptronDeep learningMatrix multiplicationTheoretical computer scienceDeep neural networksComputational complexity theoryTraining setStochastic Gradient Optimization TechniquesNeural Networks and ApplicationsMachine Learning and ELM
ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU | Litcius