aiqbench analysis
This research introduces ConQUESTA, a post-training pruning framework specifically designed for quantum neural networks (QNNs) to optimize resource usage on sparse hardware. By integrating task saliency with compiler costs and searching complete pruning masks under explicit accuracy constraints, the method significantly reduces two-qubit gates and circuit depth across various qubit counts. The approach demonstrates substantial efficiency gains without compromising model performance, addressing a critical bottleneck in deploying QNNs on near-term quantum devices.
ConQUESTA: Topology-Aware Post-Training Structural Pruning of Quantum Neural Networks
arXiv:2610.23415v1 Announce Type: new Abstract: Deploying quantum neural networks (QNNs) on sparse hardware requires preserving task accuracy while reducing compiler-induced two-qubit gates, SWAPs, and depth. We present ConQUESTA (\underline{C}onstrained \underline{Qu}antum \underline{E}ntangler \underline{S}election with \underline{T}opology \underline{A}wareness), a post training pruning framework that combines task saliency with compiler cost, screens candidate entanglers, and searches complete pruning masks under an explicit accuracy constraint. Unlike one-shot ranking, each mask is transpiled as a whole across multiple coupling topologies. Across 4-, 6-, and 8-qubit QNNs and eight model seeds at 55% pruning, ConQUESTA achieves mean resource reductions of 61.6% on Breast Cancer, 72.0% on Digits01, and 82.2% on Iris, exceeding the strongest matched simple baseline by 3.5, 1.7, and 8.9 percentage points, respectively. Fixed-mask recovery raises feasibility from 16/24 to 22/24 runs. In a fixed-k=4 scaling study on a scaling probe of 4 to 12-qubits, the raw mask space grew from 495 to 12.1M while the evaluated masks increase only from 189 to 305. Resource-weight changes alter depth/routing priorities with at most a 0.44-point mean validation shift.
Read the full article at arXiv
