Search papers, labs, and topics across Lattice.
This paper benchmarks 625 hybrid quantum neural network (HQNN) models for Chronic Kidney Disease (CKD) diagnosis, varying encoding schemes, entanglement architectures, measurement strategies, and shot settings. The study reveals strong interactions between encoding and circuit architecture, demonstrating that high performance doesn't necessitate complex circuits. Specifically, compact architectures with appropriate encodings (e.g., IQP with Ring entanglement) achieve the best accuracy/robustness/efficiency trade-off.
Turns out, simpler quantum circuits with the right data encoding can outperform complex ones in diagnosing Chronic Kidney Disease.
Hybrid Quantum Neural Networks (HQNNs) have recently emerged as a promising paradigm for near-term quantum machine learning. However, their practical performance strongly depends on design choices such as classical-to-quantum data encoding, quantum circuit architecture, measurement strategy and shots. In this paper, we present a comprehensive design space exploration of HQNNs for Chronic Kidney Disease (CKD) diagnosis. Using a carefully curated and preprocessed clinical dataset, we benchmark 625 different HQNN models obtained by combining five encoding schemes, five entanglement architectures, five measurement strategies, and five different shot settings. To ensure fair and robust evaluation, all models are trained using 10-fold stratified cross-validation and assessed on a test set using a comprehensive set of metrics, including accuracy, area under the curve (AUC), F1-score, and a composite performance score. Our results reveal strong and non-trivial interactions between encoding choices and circuit architectures, showing that high performance does not necessarily require large parameter counts or complex circuits. In particular, we find that compact architectures combined with appropriate encodings (e.g., IQP with Ring entanglement) can achieve the best trade-off between accuracy, robustness, and efficiency. Beyond absolute performance analysis, we also provide actionable insights into how different design dimensions influence learning behavior in HQNNs.
