Cluster Attention for Graph Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Platonov, Oleg, Prokhorenkova, Liudmila
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915924287684608
author Platonov, Oleg
Prokhorenkova, Liudmila
author_facet Platonov, Oleg
Prokhorenkova, Liudmila
contents Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph Transformers with global attention have been proposed; however, global attention does not take into account the graph topology and thus lacks graph-structure-based inductive biases, which are typically very important for graph machine learning tasks. In this work, we propose an alternative approach: cluster attention (CLATT). We divide graph nodes into clusters with off-the-shelf graph community detection algorithms and let each node attend to all other nodes in each cluster. CLATT provides large receptive fields while still having strong graph-structure-based inductive biases. We show that augmenting Message Passing Neural Networks or Graph Transformers with CLATT significantly improves their performance on a wide range of graph datasets including datasets from the recently introduced GraphLand benchmark representing real-world applications of graph machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cluster Attention for Graph Machine Learning
Platonov, Oleg
Prokhorenkova, Liudmila
Machine Learning
Artificial Intelligence
Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is limited by the number of message passing layers. To increase the receptive field, Graph Transformers with global attention have been proposed; however, global attention does not take into account the graph topology and thus lacks graph-structure-based inductive biases, which are typically very important for graph machine learning tasks. In this work, we propose an alternative approach: cluster attention (CLATT). We divide graph nodes into clusters with off-the-shelf graph community detection algorithms and let each node attend to all other nodes in each cluster. CLATT provides large receptive fields while still having strong graph-structure-based inductive biases. We show that augmenting Message Passing Neural Networks or Graph Transformers with CLATT significantly improves their performance on a wide range of graph datasets including datasets from the recently introduced GraphLand benchmark representing real-world applications of graph machine learning.
title Cluster Attention for Graph Machine Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.07492