Research map / Graph learning / Graph algorithms and clustering
Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
Zubin Zheng, Jiahao Wu, Shengcai Liu
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace heuristic partitioning and random initialization with the learned joint generator | QAOA^2 · In-distribution test (50 instances) | mean performance ratio: 0.8869 -> 0.8930 (vs Modularity) | Improved |
| use learned generator on unseen topologies | QAOA^2 · GKA + L (93 OOD instances) | average rank: 2.23 -> 1.46 (vs Boundary) | Improved |
| learned generator vs boundary heuristic on Ising spin glass | Neural QAOA^2 · L (Ising, OOD) | mean performance ratio: 0.8205 -> 0.8160 | Mixed |
| learned generator vs modularity on MaxCut W | Neural QAOA^2 · W (MaxCut) | average rank: 2.23 vs 2.23 | No clear effect |
| add test-time adaptation (64 steps) | Neural QAOA^2 · in-distribution test | mean performance ratio: 0.8892 (vs modularity 0.8869) | Improved |
| add pre-training of the joint generator before test-time adaptation (ablation) | Neural QAOA^2 · test-time adaptation | mean performance ratio | Improved |
| add Global Topology View to evaluator (ablation) | Neural QAOA^2 · 64 TTA steps | mean performance ratio: 0.8819 -> 0.8892 | Improved |
| add Partition-Induced Subgraph View to evaluator (ablation) | Neural QAOA^2 · 64 TTA steps | mean performance ratio: 0.8797 -> 0.8892 | Improved |
| add Quantum Parameter View to evaluator (ablation) | Neural QAOA^2 · 64 TTA steps | mean performance ratio: 0.8821 -> 0.8892 | Improved |
| add Orthogonal Complement Head instead of unconstrained cluster centers (ablation) | Neural QAOA^2 · 64 TTA steps | mean performance ratio: 0.8817 -> 0.8892 | Improved |
| add stop-gradient between partition and parameter generation (ablation) | Neural QAOA^2 · 64 TTA steps | mean performance ratio: 0.8820 -> 0.8892 | Improved |
| use generated topology-aware initial parameters instead of random (ablation) | Neural QAOA^2 · 20 QAOA steps | mean performance ratio: 0.8833 -> 0.8892 | Improved |
Closest papers by meaning
- TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search (NeurIPS 2025 · similarity 0.88)
- Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm (NeurIPS 2024 · similarity 0.88)
- A Sub-Problem Quantum Alternating Operator Ansatz for Correlation Clustering (ICML 2025 · similarity 0.88)
- MG-Net: Learn to Customize QAOA with Circuit Depth Awareness (NeurIPS 2024 · similarity 0.88)
- One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective (NeurIPS 2026 · similarity 0.87)
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
