Extending Graph Transformers with Quantum Computed Aggregation

TL;DR

This paper introduces a novel Graph Neural Network architecture that leverages quantum computing to compute global graph features, potentially enhancing GNN capabilities with quantum correlations.

Contribution

The paper presents a quantum-inspired GNN architecture using quantum correlations for aggregation weights, a novel approach not previously explored in classical GNNs.

Findings

Performs comparably to standard GNNs on benchmark datasets

Utilizes quantum correlations to capture long-range graph features

Provides theoretical insights into quantum-enhanced graph processing

Abstract

Recently, efforts have been made in the community to design new Graph Neural Networks (GNN), as limitations of Message Passing Neural Networks became more apparent. This led to the appearance of Graph Transformers using global graph features such as Laplacian Eigenmaps. In our paper, we introduce a GNN architecture where the aggregation weights are computed using the long-range correlations of a quantum system. These correlations are generated by translating the graph topology into the interactions of a set of qubits in a quantum computer. This work was inspired by the recent development of quantum processing units which enables the computation of a new family of global graph features that would be otherwise out of reach for classical hardware. We give some theoretical insights about the potential benefits of this approach, and benchmark our algorithm on standard datasets. Although not being adapted to all datasets, our model performs similarly to standard GNN architectures, and paves a promising future for quantum enhanced GNNs.