Pith. sign in

REVIEW 2 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.02075 v2 pith:R4MCTRLT submitted 2024-06-04 cs.LG cs.NE

classification cs.LGcs.NE
keywords relu-kannetworksrelubasiscomputingfunctionkolmogorov-arnoldmultiplication
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Limited by the complexity of basis function (B-spline) calculations, Kolmogorov-Arnold Networks (KAN) suffer from restricted parallel computing capability on GPUs. This paper proposes a novel ReLU-KAN implementation that inherits the core idea of KAN. By adopting ReLU (Rectified Linear Unit) and point-wise multiplication, we simplify the design of KAN's basis function and optimize the computation process for efficient CUDA computing. The proposed ReLU-KAN architecture can be readily implemented on existing deep learning frameworks (e.g., PyTorch) for both inference and training. Experimental results demonstrate that ReLU-KAN achieves a 20x speedup compared to traditional KAN with 4-layer networks. Furthermore, ReLU-KAN exhibits a more stable training process with superior fitting ability while preserving the "catastrophic forgetting avoidance" property of KAN. You can get the code in https://github.com/quiqi/relu_kan

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 13 citations worldwide. Full citation record

  1. Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks

    stat.ML 2025-08 reject novelty 5.0 of 10

    The paper states universal approximation theorems for sine-based Kolmogorov-Arnold networks, but the proof relies on an invalid lemma and an unproven matrix invertibility.

  2. Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Training in a B-spline KAN basis is equivalent to preconditioned gradient descent on a multichannel ReLU MLP, and geometric refinement plus trainable knots accelerate and improve training.

Pith tools