Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Siyuan, Song, Yunchong, Zhou, Jiayue, Lin, Zhouhan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915077956829184
author Huang, Siyuan
Song, Yunchong
Zhou, Jiayue
Lin, Zhouhan
author_facet Huang, Siyuan
Song, Yunchong
Zhou, Jiayue
Lin, Zhouhan
contents In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural information. While generally effective, these methods often rely on a fixed graph coarsening routine, leading to overly homogeneous cluster representations and loss of node-level information. In this paper, we envision the graph as a network of interconnected node sets without compressing each cluster into a single embedding. To enable effective information transfer among these node sets, we propose the Node-to-Cluster Attention (N2C-Attn) mechanism. N2C-Attn incorporates techniques from Multiple Kernel Learning into the kernelized attention framework, effectively capturing information at both node and cluster levels. We then devise an efficient form for N2C-Attn using the cluster-wise message-passing framework, achieving linear time complexity. We further analyze how N2C-Attn combines bi-level feature maps of queries and keys, demonstrating its capability to merge dual-granularity information. The resulting architecture, Cluster-wise Graph Transformer (Cluster-GT), which uses node clusters as tokens and employs our proposed N2C-Attn module, shows superior performance on various graph-level tasks. Code is available at https://github.com/LUMIA-Group/Cluster-wise-Graph-Transformer.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06746
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
Huang, Siyuan
Song, Yunchong
Zhou, Jiayue
Lin, Zhouhan
Machine Learning
In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural information. While generally effective, these methods often rely on a fixed graph coarsening routine, leading to overly homogeneous cluster representations and loss of node-level information. In this paper, we envision the graph as a network of interconnected node sets without compressing each cluster into a single embedding. To enable effective information transfer among these node sets, we propose the Node-to-Cluster Attention (N2C-Attn) mechanism. N2C-Attn incorporates techniques from Multiple Kernel Learning into the kernelized attention framework, effectively capturing information at both node and cluster levels. We then devise an efficient form for N2C-Attn using the cluster-wise message-passing framework, achieving linear time complexity. We further analyze how N2C-Attn combines bi-level feature maps of queries and keys, demonstrating its capability to merge dual-granularity information. The resulting architecture, Cluster-wise Graph Transformer (Cluster-GT), which uses node clusters as tokens and employs our proposed N2C-Attn module, shows superior performance on various graph-level tasks. Code is available at https://github.com/LUMIA-Group/Cluster-wise-Graph-Transformer.
title Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
topic Machine Learning
url https://arxiv.org/abs/2410.06746