Cluster Attention for Graph Machine Learning

TL;DR

This paper introduces Cluster Attention (CLATT), a method that enhances graph neural networks by combining community detection with attention mechanisms, improving receptive fields while preserving graph structure.

Contribution

The paper proposes CLATT, a novel attention mechanism that leverages graph communities to improve receptive fields and inductive biases in graph neural networks.

Findings

CLATT improves performance on various graph datasets.

Augmenting GNNs with CLATT enhances their receptive fields.

CLATT outperforms traditional global attention methods.

Abstract

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.