Shot-Based Quantum Encoding: A Data-Loading Paradigm for Quantum Neural Networks

TL;DR

The paper introduces Shot-Based Quantum Encoding (SBQE), a novel data embedding method for quantum neural networks that improves data loading efficiency and performance on benchmark datasets.

Contribution

SBQE is a new data encoding strategy that uses shot distributions as learnable parameters, enabling effective quantum data embedding without complex gates.

Findings

Achieves 89.1% accuracy on Semeion dataset, reducing error by 5.3% compared to amplitude encoding.

Attains 80.95% accuracy on Fashion MNIST, surpassing amplitude encoding and classical models.

Demonstrates that SBQE can be implemented with hardware-compatible protocols.

Abstract

Efficient data loading remains a bottleneck for near-term quantum machine-learning. Existing schemes (angle, amplitude, and basis encoding) either underuse the exponential Hilbert-space capacity or require circuit depths that exceed the coherence budgets of noisy intermediate-scale quantum hardware. We introduce Shot-Based Quantum Encoding (SBQE), a data embedding strategy that distributes the hardware's native resource, shots, according to a data-dependent classical distribution over multiple initial quantum states. By treating the shot counts as a learnable degree of freedom, SBQE produces a mixed-state representation whose expectation values are linear in the classical probabilities and can therefore be composed with non-linear activation functions. We show that SBQE is structurally equivalent to a multilayer perceptron whose weights are realised by quantum circuits, and we describe a hardware-compatible implementation protocol. Benchmarks on Fashion MNIST and Semeion handwritten digits, with ten independent initialisations per model, show that SBQE achieves 89.1% +/- 0.9% test accuracy on Semeion (reducing error by 5.3% relative to amplitude encoding and matching a width-matched classical network) and 80.95% +/- 0.10% on Fashion MNIST (exceeding amplitude encoding by +2.0% and a linear multilayer perceptron by +1.3%), all without any data-encoding gates.