Distribution-Guided and Constrained Quantum Machine Unlearning

2026-01-07

arXiv.org

AI Summary

This work addresses the challenge of efficiently removing the influence of specific training data in quantum machine learning without full retraining by formulating quantum machine unlearning as a constrained optimization problem. By introducing a tunable target distribution based on model similarity and an anchor retention constraint, the approach decouples the suppression of confidence for forgotten classes from the redistribution of predictions for retained classes, thereby enhancing controllability and interpretability. Integrating a variational quantum classifier with class-level unlearning mechanisms and explicit retention constraints, the method achieves significant suppression of forgotten-class confidence on the Iris and Covertype datasets while preserving retained-class performance nearly as well as full retraining.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Machine unlearning aims to remove the influence of specific training data from a learned model without full retraining. While recent work has begun to explore unlearning in quantum machine learning, existing approaches largely rely on fixed, uniform target distributions and do not explicitly control the trade-off between forgetting and retained model behaviour. In this work, we propose a distribution-guided framework for class-level quantum machine unlearning that treats unlearning as a constrained optimization problem. Our method introduces a tunable target distribution derived from model similarity statistics, decoupling the suppression of forgotten-class confidence from assumptions about redistribution among retained classes. We further incorporate an anchor-based preservation constraint that explicitly maintains predictive behaviour on selected retained data, yielding a controlled optimization trajectory that limits deviation from the original model. We evaluate the approach on variational quantum classifiers trained on the Iris and Covertype datasets. Results demonstrate sharp suppression of forgotten-class confidence, minimal degradation of retained-class performance, and closer alignment with the gold retrained model baselines compared to uniform-target unlearning. These findings highlight the importance of target design and constraint-based formulations for reliable and interpretable quantum machine unlearning.

Problem

• quantum machine unlearning
• distribution-guided
• constrained optimization
• class-level unlearning
• model forgetting

Innovation

• distribution-guided unlearning
• constrained optimization
• quantum machine unlearning
• target distribution design
• anchor-based preservation