Quantum Knowledge Distillation: State-of-the-art, Applications and Open Problems
Abstract
Knowledge distillation transfers predictions, representations, or other supervisory information between learning models and is increasingly investigated in quantum machine learning. Its applications extend beyond compression to cross-architecture transfer, circuit approximation, distributed learning, and classical deployment of models trained using quantum-derived supervision. This survey reviews these approaches using two complementary classification axes: teacher-student configuration and the role of quantum resources in the distillation process. Quantum-inspired methods are discussed separately from methods that simulate quantum computations classically or execute them on quantum hardware. We explain how measurement probabilities, expectation values, classical readouts, state overlaps, and circuit-level objectives support different transfer mechanisms. We then critically assess the presented results against baseline design, execution conditions, uncertainty, and resource costs. The evidence shows that distillation can improve selected quantum students, but benefits are task- and architecture-dependent, and several studies find negligible gains or even performance degradation. Evaluations on physical quantum hardware remain limited, with some testing individual quantum components rather than complete learning pipelines. Heterogeneous protocols and incomplete resource reporting prevent general conclusions about practical quantum advantage. We identify priorities for controlled benchmarking, noise-aware learning, reproducible evaluation, and efficient transfer between quantum and classical models.
Related
- Complexity and Applications of Nearest Stabilizer Product State Problems
- Solving wave propagation problems via geometric quantum state preparation on dispersion manifolds
- Riemannian Formulation of Sample-Based Quantum Krylov Solvers for Elliptic Problems: Energy-Norm Guarantees and Duct-Flow Applications
- Regret Lower Bound for Online Learning of Quantum States with Logarithmic Loss, with Applications to Quantum State Tomography and Confidence Sequences for Matrix Means
- A Spectrum-Based Converse for Quantum State Discrimination and Its Applications to Classical-Quantum Channel Coding
BibTeX
@misc{alsulaiti2026quantum,
title = {{Quantum Knowledge Distillation: State-of-the-art, Applications and Open Problems}},
author = {Aldana Al-Sulaiti and Kuan-Cheng Chen and Muhammad Bilal Akram Dastagir and Ahmed Farouk and Saif Al-Kuwari},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08461},
eprint = {2611.08461},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08461},
}
RIS
TY - UNPB
TI - Quantum Knowledge Distillation: State-of-the-art, Applications and Open Problems
AU - Aldana Al-Sulaiti
AU - Kuan-Cheng Chen
AU - Muhammad Bilal Akram Dastagir
AU - Ahmed Farouk
AU - Saif Al-Kuwari
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.08461
UR - https://arxiv.org/abs/2611.08461
AB - Knowledge distillation transfers predictions, representations, or other supervisory information between learning models and is increasingly investigated in quantum machine learning. Its applications extend beyond compression to cross-architecture transfer, circuit approximation, distributed learning, and classical deployment of models trained using quantum-derived supervision. This survey reviews these approaches using two complementary classification axes: teacher-student configuration and the role of quantum resources in the distillation process. Quantum-inspired methods are discussed separately from methods that simulate quantum computations classically or execute them on quantum hardware. We explain how measurement probabilities, expectation values, classical readouts, state overlaps, and circuit-level objectives support different transfer mechanisms. We then critically assess the presented results against baseline design, execution conditions, uncertainty, and resource costs. The evidence shows that distillation can improve selected quantum students, but benefits are task- and architecture-dependent, and several studies find negligible gains or even performance degradation. Evaluations on physical quantum hardware remain limited, with some testing individual quantum components rather than complete learning pipelines. Heterogeneous protocols and incomplete resource reporting prevent general conclusions about practical quantum advantage. We identify priorities for controlled benchmarking, noise-aware learning, reproducible evaluation, and efficient transfer between quantum and classical models.
ER -