Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.06296 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916782649901056 |
|---|---|
| author | Afia, Hanaa El Ohamouddou, Said Chiheb, Raddouane Afia, Abdellatif El |
| author_facet | Afia, Hanaa El Ohamouddou, Said Chiheb, Raddouane Afia, Abdellatif El |
| contents | We introduce Jacobi-KAN-DGCNN, a framework that integrates Dynamic Graph Convolutional Neural Network (DGCNN) with Jacobi Kolmogorov-Arnold Networks (KAN) for the classification of three-dimensional point clouds. This method replaces Multi-Layer Perceptron (MLP) layers with adaptable univariate polynomial expansions within a streamlined DGCNN architecture, circumventing deep levels for both MLP and KAN to facilitate a layer-by-layer comparison. In comparative experiments on the ModelNet40 dataset, KAN layers employing Jacobi polynomials outperform the traditional linear layer-based DGCNN baseline in terms of accuracy and convergence speed, while maintaining parameter efficiency. Our results demonstrate that higher polynomial degrees do not automatically improve performance, highlighting the need for further theoretical and empirical investigation to fully understand the interactions between polynomial bases, degrees, and the mechanisms of graph-based learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06296 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Graph CNN with Jacobi Kolmogorov-Arnold Networks for 3D Classification of Point Sets Afia, Hanaa El Ohamouddou, Said Chiheb, Raddouane Afia, Abdellatif El Machine Learning Artificial Intelligence We introduce Jacobi-KAN-DGCNN, a framework that integrates Dynamic Graph Convolutional Neural Network (DGCNN) with Jacobi Kolmogorov-Arnold Networks (KAN) for the classification of three-dimensional point clouds. This method replaces Multi-Layer Perceptron (MLP) layers with adaptable univariate polynomial expansions within a streamlined DGCNN architecture, circumventing deep levels for both MLP and KAN to facilitate a layer-by-layer comparison. In comparative experiments on the ModelNet40 dataset, KAN layers employing Jacobi polynomials outperform the traditional linear layer-based DGCNN baseline in terms of accuracy and convergence speed, while maintaining parameter efficiency. Our results demonstrate that higher polynomial degrees do not automatically improve performance, highlighting the need for further theoretical and empirical investigation to fully understand the interactions between polynomial bases, degrees, and the mechanisms of graph-based learning. |
| title | Dynamic Graph CNN with Jacobi Kolmogorov-Arnold Networks for 3D Classification of Point Sets |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.06296 |