Metraipolis › archive › dc_cd5a0b268d3e
QSTAR: Quantum Selective Transfer with Adaptive Routing — arXiv:2607.21411
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2607.21411
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:12:13.839Z
- SHA-256 of the archived text
2918773c8a240859ce7b27b93905cc70914be38aaee3d747f36bfe7eb8625f85- Stable URL of this page
https://metraipolis.com/documento/dc_cd5a0b268d3e
How to cite
QSTAR: Quantum Selective Transfer with Adaptive Routing — arXiv:2607.21411 — arXiv (en), https://arxiv.org/abs/2607.21411 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd5a0b268d3e (Metraipolis archive dc_cd5a0b268d3e, sha256 2918773c8a240859ce7b27b93905cc70914be38aaee3d747f36bfe7eb8625f85)
BibTeX
@misc{dccd5a0b268d3e,
title = {QSTAR: Quantum Selective Transfer with Adaptive Routing — arXiv:2607.21411},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2607.21411},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd5a0b268d3e; sha256 2918773c8a240859ce7b27b93905cc70914be38aaee3d747f36bfe7eb8625f85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2607.21411. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Quantum transfer learning (QTL) is often evaluated by replacing a classical classifier with a fixed variational quantum head, but this hides a key question: when is the quantum branch actually useful? We propose QSTAR: Quantum Selective Transfer with Adaptive Routing, a selective QTL framework that keeps high-confidence classical predictions and routes only low-confidence samples to a fallback branch. Using a frozen ResNet18 backbone on Fashion-MNIST, we compare manually designed QTL heads, KetGPT-designed quantum heads, and parameter-matched classical baselines under a common data split and optimization schedule. Standard QTL heads reach at most 57.0% accuracy, while the strongest KetGPT head in the main filtered sweep reaches 78.5% accuracy and 0.785 F1-score. Although the strongest fixed classical head remains higher at 81.6%, selective routing gives the quantum branch a clearer role. On low-confidence samples, KetGPT #180 improves accuracy over a parameter-matched MLP fallback by 6.82, 4.31, and 3.03 percentage points at thresholds of 0.70, 0.80, and 0.90. At the full-system level, Adaptive KetGPT-QTL reaches 80.9% accuracy and 0.807 F1-score, outperforming the adaptive classical baseline. A separate compact-circuit ablation identifies KetGPT #160 as a stronger fixed-head candidate, reaching 81.9% accuracy with only 10 quantum parameters and 9 gates. These results suggest that architecture-searched quantum heads are most useful as targeted fallback branches for uncertain inputs rather than uniform replacements for classical classifiers. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2607.21411 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:54:14.807Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).