# Hardware Acceleration of Kolmogorov-Arnold Network (KAN) for Lightweight Edge Inference

arXiv: https://arxiv.org/abs/2409.11418 · HTML: https://mlsanity.com/paper/2409.11418/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2024.

## Built on by (most cited first, 11 of 11)

- [ChemKANs for Combustion Chemistry Modeling and Acceleration](https://mlsanity.com/paper/2504.12580/) (2025)
- [KANtize: Exploring Low-bit Quantization of Kolmogorov-Arnold Networks for Efficient Inference](https://mlsanity.com/paper/2603.17230/) (2026)
- [KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrays](https://mlsanity.com/paper/2512.00055/) (2025)
- [Fully analogue in-memory neural computing via quantum tunneling effect](https://mlsanity.com/paper/2510.23638/) (2025)
- [QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks](https://mlsanity.com/paper/2511.18689/) (2025)
- [Lookup multivariate Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2509.07103/) (2025)
- [BiKA: Kolmogorov-Arnold-Network-inspired Ultra Lightweight Neural Network Hardware Accelerator](https://mlsanity.com/paper/2602.23455/) (2026)
- [Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2604.03345/) (2026)
- [Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2602.02056/) (2026)
- [Physical Analogue Kolmogorov-Arnold Networks based on Reconfigurable Nonlinear-Processing Units](https://mlsanity.com/paper/2602.07518/) (2026)
- [An Embedded RISC-V Evaluation of Kolmogorov--Arnold Networks in Hard-Constrained Recurrent Physics-Informed Models](https://mlsanity.com/paper/2608.00737/) (2026)

## Abstract (arXiv)

Recently, a novel model named Kolmogorov-Arnold Networks (KAN) has been proposed with the potential to achieve the functionality of traditional deep neural networks (DNNs) using orders of magnitude fewer parameters by parameterized B-spline functions with trainable coefficients. However, the B-spline functions in KAN present new challenges for hardware acceleration. Evaluating the B-spline functions can be performed by using look-up tables (LUTs) to directly map the B-spline functions, thereby reducing computational resource requirements. However, this method still requires substantial circuit resources (LUTs, MUXs, decoders, etc.). For the first time, this paper employs an algorithm-hardware co-design methodology to accelerate KAN. The proposed algorithm-level techniques include Alignment-Symmetry and PowerGap KAN hardware aware quantization, KAN sparsity aware mapping strategy, and circuit-level techniques include N:1 Time Modulation Dynamic Voltage input generator with analog-CIM (ACIM) circuits. The impact of non-ideal effects, such as partial sum errors caused by the process variations, has been evaluated with the statistics measured from the TSMC 22nm RRAM-ACIM prototype chips. With the best searched hyperparameters of KAN and the optimized circuits implemented in 22 nm node, we can reduce hardware area by 41.78x, energy by 77.97x with 3.03% accuracy boost compared to the traditional DNN hardware.