QAOA Parameter Transferability for Maximum Independent Set using Graph Attention Networks
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Quantum Variational Approaches to the Maximum Independent Set Problem at Utility Scale
Variational quantum methods with spectral preprocessing, CVaR optimization, and ancilla-assisted superposition solve maximum independent set to optimality on graphs up to 180 vertices, claimed as the largest such gate...
-
QAOA Parameter Transfer for Hypergraphs
Analytical reweighting rules for QAOA parameters on hypergraphs improve performance by adjusting mixing terms beyond previous graph-based methods.
-
Quantum Variational Approaches to the Maximum Independent Set Problem at Utility Scale
Variational quantum methods with spectral reordering, sparsification, CVaR optimization, and ancilla-assisted superposition solve MIS to optimality on 64-, 99-, and 180-vertex graphs, the largest such gate-based demon...
-
Setting angles in quantum approximate optimization at utility-scale
The paper benchmarks approximation techniques and transfer learning for setting QAOA angles at utility scale and extracts operational guidance from hardware-validated results.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.