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.
翻译:最近,随着信息传递神经网络的局限性越来越明显,社区在设计新的图形神经网络(GNN)方面做出了努力。这导致了使用Laplacian Eigenmaps等全球图形特征的图形变异器的出现。在我们的论文中,我们引入了一个GNN结构,其中总加权数使用量子系统的远程相关性计算。这些关联是通过将图形表层学转化为量子计算机中一组qubit的相互作用而产生的。这项工作受到量子处理器的近期开发的启发,该设备使得能够计算出一个新的全球图形特征系列,这些特征在古典硬件中将无法达到。我们对这种方法的潜在好处有一些理论见解,并将我们的算法以标准数据集作为基准。尽管我们没有对所有数据集进行调整,但我们的模型与GNNS标准结构类似,并且为量子增强的GNNN提供了有希望的未来。