Curator's Take
AI Commentary
This article provides the first systematic map of how knowledge‑distillation techniques can be leveraged across quantum and classical machine‑learning models, highlighting both compression gains and more ambitious cross‑architecture transfers such as circuit approximation and distributed training. By juxtaposing teacher–student configurations with the specific quantum resources used—ranging from raw measurement probabilities to full‑circuit objectives—it clarifies where genuine quantum advantage has been demonstrated versus where results remain marginal or hardware‑limited. The survey’s critical assessment of experimental evidence and its call for standardized reporting give researchers a concrete roadmap for turning these promising ideas into reproducible, scalable applications.
— Mark Eatherly
Summary
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.