Amplitude-based Input Attribution in Quantum Learning via Integrated Gradients

ICLR 2026 Conference Submission14522 Authors

Keywords: Quantum Computing, Quantum Machine Learning, Interpretability in QML

TL;DR: We introduce HattriQ, a technique for computing the input attribution scores of quantum machine learning models.

Abstract: Quantum machine learning (QML) algorithms have demonstrated early promise across hardware platforms, but remain difficult to interpret due to the inherent opacity of quantum state evolution. Widely-used classical interpretability methods, such as integrated gradients and surrogate-based sensitivity analysis, are not directly compatible with quantum circuits due to measurement collapse and the exponential complexityof simulating state evolution. In this work, we introduce HATTRIQ, a general-purpose framework to compute amplitude-based input attribution scores in circuit-based QML models. HATTRIQ supports the widely-used input amplitude embedding feature encoding scheme and uses a Hadamard test–based construction to compute input gradients directly on quantum hardware to generate provably faithful attributions. We validate HATTRIQ on classification tasks across several datasets (Bars and Stripes, MNIST, and FashionMNIST).

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 14522