Quantum Logic Gates for Accelerating Graph Convolutional Network Operations

Abstract

Graph Convolutional Networks (GCNs) have been widely used to learn from graph structured data, but GCNs suffer from a high complexity in the handling of large-scale graphs, since processing large graphs demands recursive aggregation of features and high dimensional node embeddings. Scalability can become a tight bottleneck in traditional CPU/GPU implementations, which detracts from their ability to be used in real-time and resource-constrained settings. In this study, Quantum-assisted GCN (QGCN) is proposed as a quantum-assisted GCN model with the help of quantum logic gates, thereby speeding up the graph convolution operation. The idea proposed in the paper is to represent the queries and graph features as qubits and use a sequence of both single and multi-qubit gates such as Hadamard, CNOT and rotation gates with learned parameters to convolute a graph over qubits simultaneously. Once measured, the quantum state is represented classically, in the form of features, which are then used to feed downstream node classification tasks. On the benchmark datasets Cora, PubMed, and Citeseer, experiments show that the quantum-assisted GCN delivers substantial speed-up over a classical implementation, approaches the performance of the GPU-optimized implementation, and maintains classification within a 0.5–1% margin. If NISQ simulators are to scale up to very large graphs, there are resource utilization issues, which is manageable for current simulators given the number of qubits and gate depth. These results show concrete compromises between acceleration, accuracy preservation, and quantum resource efficiency. The results of this study could be useful for designing hybrid quantum-classical graph learning architectures and represent one possible method for performing faster GCN operations in both academic research and applications. Extensions and developments are focused on multi-layer quantum GCNs as well as hybrid architectures for large-scale GWs and real-time deployment strategies.