ConQUESTA: Topology-Aware Post-Training Structural Pruning of Quantum Neural Networks
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.
Related
- Efficient Transport Networks through Edge Pruning by Relative Resistance
- When Edge Importance Disagrees: Resistance-Ranked versus Betweenness Pruning on Urban Road Networks
- Structural identification in general crystalline systems via Voronoi cell topology
- Zero-shot rib design: merging training-free generative prior with topology optimization
- Many-body topology in parity-preserving tensor networks
BibTeX
@misc{rehman2026conquesta,
title = {{ConQUESTA: Topology-Aware Post-Training Structural Pruning of Quantum Neural Networks}},
author = {Saim Rehman and Muhammad Shafique},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.23415},
eprint = {2610.23415},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.23415},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ConQUESTA: Topology-Aware Post-Training Structural Pruning of Quantum Neural Networks
AU - Saim Rehman
AU - Muhammad Shafique
PY - 2026
DA - 2026/10/16
PB - arXiv
DO - 10.48550/arxiv.2610.23415
UR - https://arxiv.org/abs/2610.23415
AB - 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.
ER -