# Introducing the Short-Time Fourier Kolmogorov Arnold Network: A Dynamic Graph CNN Approach for Tree Species Classification in 3D Point Clouds

arXiv: https://arxiv.org/abs/2503.23647 · HTML: https://mlsanity.com/paper/2503.23647/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 56 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Kolmogorov-Arnold Networks are Radial Basis Function Networks](https://mlsanity.com/paper/2405.06721/) (2024)
- [The Kolmogorov-Arnold representation theorem revisited](https://mlsanity.com/paper/2007.15884/) (2020)
- [Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud](https://mlsanity.com/paper/2012.10921/) (2020)
- [PVT: Point-Voxel Transformer for Point Cloud Learning](https://mlsanity.com/paper/2108.06076/) (2021)
- [ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU](https://mlsanity.com/paper/2406.02075/) (2024)
- [PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets](https://mlsanity.com/paper/2410.10084/) (2024)
- [Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset](https://mlsanity.com/paper/2408.06507/) (2024)
- [Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognition](https://mlsanity.com/paper/2204.03957/) (2022)
- [Graph Fairing Convolutional Networks for Anomaly Detection](https://mlsanity.com/paper/2010.10274/) (2020)
- [GANN: Graph Alignment Neural Network for Semi-Supervised Learning](https://mlsanity.com/paper/2303.07778/) (2023)

## Built on by (most cited first, 4 of 4)

- [MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classification](https://mlsanity.com/paper/2507.12602/) (2025)
- [ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems](https://mlsanity.com/paper/2508.20232/) (2025)
- [Smoothing-Based Conformal Prediction for Balancing Efficiency and Interpretability](https://mlsanity.com/paper/2509.22529/) (2025)
- [LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning](https://mlsanity.com/paper/2604.10780/) (2026)

## Abstract (arXiv)

Accurate classification of tree species based on Terrestrial Laser Scanning (TLS) and Airborne Laser Scanning (ALS) is essential for biodiversity conservation. While advanced deep learning models for 3D point cloud classification have demonstrated strong performance in this domain, their high complexity often hinders the development of efficient, low-computation architectures. In this paper, we introduce STFT-KAN, a novel Kolmogorov-Arnold network that integrates the Short-Time Fourier Transform (STFT), which can replace the standard linear layer with activation. We implemented STFT-KAN within a lightweight version of DGCNN, called liteDGCNN, to classify tree species using the TLS data. Our experiments show that STFT-KAN outperforms existing KAN variants by effectively balancing model complexity and performance with parameter count reduction, achieving competitive results compared to MLP-based models. Additionally, we evaluated a hybrid architecture that combines MLP in edge convolution with STFT-KAN in other layers, achieving comparable performance to MLP models while reducing the parameter count by 50% and 75% compared to other KAN-based variants. Furthermore, we compared our model to leading 3D point cloud learning approaches, demonstrating that STFT-KAN delivers competitive results compared to the state-of-the-art method PointMLP lite with an 87% reduction in parameter count.