GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ai, Guoguo, Pang, Guansong, Qiao, Hezhe, Gao, Yuan, Yan, Hui
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915310903230464
author Ai, Guoguo
Pang, Guansong
Qiao, Hezhe
Gao, Yuan
Yan, Hui
author_facet Ai, Guoguo
Pang, Guansong
Qiao, Hezhe
Gao, Yuan
Yan, Hui
contents Graph Transformers (GTs) have demonstrated remarkable performance in graph representation learning over popular graph neural networks (GNNs). However, self--attention, the core module of GTs, preserves only low-frequency signals in graph features, leading to ineffectiveness in capturing other important signals like high-frequency ones. Some recent GT models help alleviate this issue, but their flexibility and expressiveness are still limited since the filters they learn are fixed on predefined graph spectrum or spectral order. To tackle this challenge, we propose a Graph Fourier Kolmogorov-Arnold Transformer (GrokFormer), a novel GT model that learns highly expressive spectral filters with adaptive graph spectrum and spectral order through a Fourier series modeling over learnable activation functions. We demonstrate theoretically and empirically that the proposed GrokFormer filter offers better expressiveness than other spectral methods. Comprehensive experiments on 10 real-world node classification datasets across various domains, scales, and graph properties, as well as 5 graph classification datasets, show that GrokFormer outperforms state-of-the-art GTs and GNNs. Our code is available at https://github.com/GGA23/GrokFormer
format Preprint
id arxiv_https___arxiv_org_abs_2411_17296
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
Ai, Guoguo
Pang, Guansong
Qiao, Hezhe
Gao, Yuan
Yan, Hui
Machine Learning
Artificial Intelligence
Graph Transformers (GTs) have demonstrated remarkable performance in graph representation learning over popular graph neural networks (GNNs). However, self--attention, the core module of GTs, preserves only low-frequency signals in graph features, leading to ineffectiveness in capturing other important signals like high-frequency ones. Some recent GT models help alleviate this issue, but their flexibility and expressiveness are still limited since the filters they learn are fixed on predefined graph spectrum or spectral order. To tackle this challenge, we propose a Graph Fourier Kolmogorov-Arnold Transformer (GrokFormer), a novel GT model that learns highly expressive spectral filters with adaptive graph spectrum and spectral order through a Fourier series modeling over learnable activation functions. We demonstrate theoretically and empirically that the proposed GrokFormer filter offers better expressiveness than other spectral methods. Comprehensive experiments on 10 real-world node classification datasets across various domains, scales, and graph properties, as well as 5 graph classification datasets, show that GrokFormer outperforms state-of-the-art GTs and GNNs. Our code is available at https://github.com/GGA23/GrokFormer
title GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.17296