Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study

TL;DR

This paper empirically investigates machine unlearning in hybrid quantum-classical neural networks, revealing how quantum model characteristics influence unlearning effectiveness and trade-offs.

Contribution

It adapts classical unlearning methods to quantum models, introduces new strategies, and provides empirical insights into unlearning behavior in quantum neural networks.

Findings

Quantum models can support effective unlearning.

Shallow VQCs show high stability with minimal memorization.

Deeper hybrid models exhibit trade-offs between utility and forgetting.

Abstract

We present the first empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantum-augmented architectures remains largely unexplored. First, we adapt a broad suite of unlearning methods to quantum settings, including gradient-based, distillation-based, regularization-based and certified techniques. Second, we introduce two new unlearning strategies tailored to hybrid models. Experiments across Iris, MNIST, and Fashion-MNIST, under both subset removal and full-class deletion, reveal that quantum models can support effective unlearning, but outcomes depend strongly on circuit depth, entanglement structure, and task complexity. Shallow VQCs display high intrinsic stability with minimal memorization, whereas deeper hybrid models exhibit stronger trade-offs between utility, forgetting strength, and alignment with retrain oracle. We find that certain methods, e.g. EU-k, LCA, and Certified Unlearning, consistently provide the best balance across metrics. These findings establish baseline empirical insights into quantum machine unlearning and highlight the need for quantum-aware algorithms and theoretical guarantees, as quantum machine learning systems continue to expand in scale and capability. We publicly release our code at: https://github.com/CrivoiCarla/HQML.