mlsanityData to 14 Oct 2026

QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks

arXiv 2511.18689 ↗First posted 24 Nov 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Kolmogorov--Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-precision deployment due to heterogeneous parameter distributions. We introduce QuantKAN, the first unified framework for quantization-aware training (QAT) and post-training quantization (PTQ) of KANs. The framework employs branch-aware quantizers for base and spline parameters and extends modern QAT and PTQ methods to spline-based layers across EfficientKAN, FastKAN, PyKAN, and KAGN. Experiments on MNIST, CIFAR-10/100, TinyImageNet, and ImageNet provide the first unified QAT/PTQ KAN benchmarks and show that DSQ is the most robust QAT method at aggressive low-bit settings, while GPTQ is the strongest PTQ method at moderate precision. Sensitivity analyses reveal architecture-specific failure modes: spline/basis parameters dominate in FastKAN, while base or scaling parameters dominate in EfficientKAN, GRAM, and PyKAN. Vivado HLS estimates on a Xilinx UltraScale+ device further suggest up to 3.32× throughput and 7.7× lower estimated dynamic energy per inference under W4A4, exposing a residual basis-evaluation tax that motivates basis-aware microarchitecture. QuantKAN is available at https://github.com/OSU-STARLAB/QuantKAN/.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

23 of 33 references.

References · 23

  1. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  5. 2019Learned Step Size Quantizationcited by 628
  6. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  7. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  8. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  9. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  10. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  11. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
  12. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
11 more
  1. 2019HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networkscited by 261
  2. 2021I-BERT: Integer-only BERT Quantizationcited by 255
  3. 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
  4. 2020LSQ+: Improving low-bit quantization through learnable offsets and better initializationcited by 189
  5. 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 160
  6. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 151
  7. 2024Kolmogorov-Arnold Networks are Radial Basis Function Networkscited by 128
  8. 2020Bayesian Bits: Unifying Quantization and Pruningcited by 94
  9. 2024Exploring the Limitations of Kolmogorov-Arnold Networks in Classification: Insights to Software Training and Hardware Implementationcited by 22
  10. 2024Hardware Acceleration of Kolmogorov-Arnold Network (KAN) for Lightweight Edge Inferencecited by 11
  11. 2025MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Networkcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026KANtize: Exploring Low-bit Quantization of Kolmogorov-Arnold Networks for Efficient Inferencecited by 4
  2. 2026Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LUT-KAN: Segment-wise LUT Quantization for Fast KAN Inference
  2. 2026FuncCode: Compressing Kolmogorov--Arnold Networks in Function Space with Hardware-Aware Quantization
  3. 2022QFT: Post-training quantization via fast joint finetuning of all degrees of freedom
  4. 2025SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
  5. 2024COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization
  6. 2024Improving Quantization-aware Training of Low-Precision Network via Block Replacement on Full-Precision Counterpart
  7. 2026Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization
  8. 2024Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview