QNAS applies multi-objective NAS with a SuperCircuit and NSGA-II to discover compact HQNN architectures that trade off accuracy against runtime and cutting overhead, achieving 97.16% on MNIST (8 qubits), 87.38% on Fashion-MNIST (5 qubits), and 100% on Iris (4 qubits).
Continuous evolution for efficient quantum architecture search,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
QNAS: A Neural Architecture Search Framework for Accurate and Efficient Quantum Neural Networks
QNAS applies multi-objective NAS with a SuperCircuit and NSGA-II to discover compact HQNN architectures that trade off accuracy against runtime and cutting overhead, achieving 97.16% on MNIST (8 qubits), 87.38% on Fashion-MNIST (5 qubits), and 100% on Iris (4 qubits).