When do quantum views help? Complementary classical-quantum representations in multi-view fusion
Abstract
Recent studies have reported promising results from quantum machine learning in drug discovery, healthcare, materials science and cybersecurity. Research includes comparisons with classical machine learning algorithms and the development of sequential hybrid pipelines. We propose that fusion can improve prediction when classical and quantum representations capture complementary predictive relationships. Our classical-quantum multi-view framework preserves the full classical input alongside simulated quantum features. Concatenation and attention combine the views; single-view comparisons, replacement and masking controls assess both views' contributions. Controlled angular-polynomial experiments distinguish targets adequately represented by a single view from those that depend on complementary angular and polynomial relationships. For these mixed targets, fusion improves prediction by combining the relevant feature sets, while matched classical representations recover the same benefit, linking the improvement to their complementary predictive content. Controlled classification tests further show that gains depend on alignment between the chosen representation and the target, and on a suitable fusion rule. Benchmark validation shows improved mean predictive performance over classical baselines on Wine, Wisconsin Diagnostic Breast Cancer, three-class Fashion-MNIST and Steel Plates Faults within the evaluated protocols. Classical replacement and masking controls remain competitive, classical baselines lead on Digits and Covertype, and outcomes with missing or corrupted views depend on the available inputs. These findings support evaluating quantum representations for their complementary predictive contribution and matching the representation and fusion strategy to the target relationships.
Related
- Diversity-Aware Ensemble of Quantum-Classical Models via Combinatorial Fusion
- Feature-Adaptive Fusion in Hybrid Quantum-Classical Neural Networks for Robust Biomedical Image Classification
- When Complementary Measurements Count the Same Classical Bit Twice: Counterexamples to CQC, ECQC, and Complementarity-Based Certification
- Target-space fusion of classical topological defects
- Two-body control of noiseless subsystems with mixed SU(3) representations lifts teleportation above the classical fidelity limit
BibTeX
@misc{alavi2026when,
title = {{When do quantum views help? Complementary classical-quantum representations in multi-view fusion}},
author = {Azadeh Alavi and Fatemeh Kouchmeshki and Hossein Akhoundi and Yongli Re and Abdolrahman Alavi and Muhammad Usman},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.21395},
eprint = {2610.21395},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.21395},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - When do quantum views help? Complementary classical-quantum representations in multi-view fusion
AU - Azadeh Alavi
AU - Fatemeh Kouchmeshki
AU - Hossein Akhoundi
AU - Yongli Re
AU - Abdolrahman Alavi
AU - Muhammad Usman
PY - 2026
DA - 2026/10/15
PB - arXiv
DO - 10.48550/arxiv.2610.21395
UR - https://arxiv.org/abs/2610.21395
AB - Recent studies have reported promising results from quantum machine learning in drug discovery, healthcare, materials science and cybersecurity. Research includes comparisons with classical machine learning algorithms and the development of sequential hybrid pipelines. We propose that fusion can improve prediction when classical and quantum representations capture complementary predictive relationships. Our classical-quantum multi-view framework preserves the full classical input alongside simulated quantum features. Concatenation and attention combine the views; single-view comparisons, replacement and masking controls assess both views' contributions. Controlled angular-polynomial experiments distinguish targets adequately represented by a single view from those that depend on complementary angular and polynomial relationships. For these mixed targets, fusion improves prediction by combining the relevant feature sets, while matched classical representations recover the same benefit, linking the improvement to their complementary predictive content. Controlled classification tests further show that gains depend on alignment between the chosen representation and the target, and on a suitable fusion rule. Benchmark validation shows improved mean predictive performance over classical baselines on Wine, Wisconsin Diagnostic Breast Cancer, three-class Fashion-MNIST and Steel Plates Faults within the evaluated protocols. Classical replacement and masking controls remain competitive, classical baselines lead on Digits and Covertype, and outcomes with missing or corrupted views depend on the available inputs. These findings support evaluating quantum representations for their complementary predictive contribution and matching the representation and fusion strategy to the target relationships.
ER -