QAOA Parameter Transferability for Maximum Independent Set using Graph Attention Networks
This work addresses the parameter optimization bottleneck in QAOA for combinatorial optimization, offering a scalable solution for quantum computing on NISQ devices, though it is incremental as it builds on existing methods like GATs and distributed algorithms.
The authors tackled the challenge of optimizing variational parameters in the Quantum Approximate Optimization Algorithm (QAOA) for Maximum Independent Set problems by proposing a parameter transfer scheme using Graph Attention Networks (GATs) and integrating it into a hybrid distributed algorithm, achieving competitive results against a state-of-the-art classical solver on graphs with thousands of vertices.
The quantum approximate optimization algorithm (QAOA) is one of the promising variational approaches of quantum computing to solve combinatorial optimization problems. In QAOA, variational parameters need to be optimized by solving a series of nonlinear, nonconvex optimization programs. In this work, we propose a QAOA parameter transfer scheme using Graph Attention Networks (GAT) to solve Maximum Independent Set (MIS) problems. We prepare optimized parameters for graphs of 12 and 14 vertices and use GATs to transfer their parameters to larger graphs. Additionally, we design a hybrid distributed resource-aware algorithm for MIS (HyDRA-MIS), which decomposes large problems into smaller ones that can fit onto noisy intermediate-scale quantum (NISQ) computers. We integrate our GAT-based parameter transfer approach to HyDRA-MIS and demonstrate competitive results compared to KaMIS, a state-of-the-art classical MIS solver, on graphs with several thousands vertices.