- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
Existing quantum architecture search (QAS) primarily selects architectures based on predictive accuracy and does not account for potential post-deployment unlearning needs. This paper conducts an empirical study and reveals for the first time that quantum model architecture itself can substantially affect unlearning capability, even among architectures with comparable predictive accuracy. Building on this observation, the paper proposes Unlearning-driven Quantum Architecture Search (UQAS), a framework that incorporates unlearning capability into QAS to better prepare quantum models for post-deployment unlearning requests.
Critical strengths
-
The entry point of the paper is novel. This is the first paper to empirically reveal that quantum architectures with comparable predictive accuracy can exhibit substantially different unlearning capability.
-
Empirical studies are meaningful. Experiments on Fashion-MNIST architectures attain the same validation accuracy of 98.5%, yet their mean TV distances are 0.0081 and 0.3894, this motivates the study of the method.
-
Experiments are carried out across sixteen evaluation scenarios spanning four diverse datasets and four accuracy-based QAS methods.
Critical weaknesses
-
Total variation (TV) distance may not guarantee data removal.
-
The largest circuit width is ten qubits in the experiments, which is limited. And tasks like Fashion-MNIST, WDBC are restricted to simple classification. The experiments may be extended to more complex settings.
-
The paper uses masked fine tuning of the trained parameters as the default unlearning operator and discusses full fine tuning, NegGrad+, adapted diagonal influence in the appendix. It is not clear whether UQAS just works on fine tuning-based approaches.
Questions for authors
See Weaknesses.
4 comments
Response to Reviewer BKeG (Part 2/2)
To W3: We apologize for causing this confusion. The unlearning methods evaluated in the paper are mainly based on fine tuning, which gave the impression that UQAS only works with such approaches. However, UQAS is in fact not limited to methods based on fine tuning. To demonstrate this, we have added two unlearning methods that perform no fine tuning (Table C). The first adapts the trajectory correction of the Hessian free method HF [1] and the second adapts the Fisher correction of Golatkar et al. [2]. Both only combine derivative statistics cached beforehand and bring the model closer to retraining than leaving it unchanged. UCE scores candidates using the same unlearning method as in evaluation.
Table C: Mean unlearning discrepancy without fine tuning.
| Unlearning method | Task | Baseline | UQAS-Select | UQAS-Design |
|---|---|---|---|---|
| HF | Digits | 0.005730 | 0.004860 | 0.000517 |
| Fashion-MNIST | 0.001073 | 0.000087 | 0.000348 | |
| WDBC | 0.016831 | 0.003230 | 0.003425 | |
| TFIM | 0.002293 | 0.000006 | 0.000008 | |
| Fisher | Digits | 0.026916 | 0.019709 | 0.003085 |
| Fashion-MNIST | 0.007418 | 0.002306 | 0.001799 | |
| WDBC | 0.049337 | 0.017177 | 0.025045 | |
| TFIM | 0.020261 | 0.001850 | 0.001740 |
Select and Design both lower the mean TV on every task under both methods, by 15.2% to 99.7%. At the same time, the absolute decrease in mean test accuracy compared with the baseline is at most 1.00%. Together with the four unlearning methods of Table 13 (Appendix C.5), UQAS thus lowers the discrepancy under six methods. We will add the results for these two methods to the revised version.
Thank you again for your constructive comments. We would be glad to answer any further questions.
[1] Qiao et al. Hessian-Free Online Certified Unlearning. ICLR 2025.
[2] Golatkar et al. Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks. CVPR 2020.
I thank the authors for the detailed response. I will keep my score.
Thank you for your time and continued support. We deeply value your recognition of the novelty of our work and the breadth of our experiments. Your feedback has been instrumental in strengthening our paper. Thank you again for your constructive engagement throughout the review process.
Response to Reviewer BKeG (Part 1/2)
Thank you very much for your careful review and for your support of our work.
To W1: This is an insightful observation. We agree that a small TV distance does not by itself certify data removal, as explained in Appendix A.5. Retraining without the removed data is the gold standard for evaluating unlearning [1]. To assess closeness to retraining, we use TV, a widely used probability metric [2]. TV quantifies differences between the output distributions of the unlearned and retrained models, with smaller values indicating greater similarity [3].
Beyond output similarity, we examined whether models with lower TV also leak less membership information. To do so, we conducted a membership inference audit adapted from Sarmasarkar et al. [4]. In this audit, an attacker uses outputs of the unlearned model to predict whether the removed batch was part of the original training data. Table A reports the area under the receiver operating characteristic curve (AUC) for the attack under full fine tuning, averaged over the four tasks. UQAS achieves a lower mean attack AUC than the baseline.
Table A: Attack AUC of the batch audit (retraining: 0.5000).
The AUC gap is statistically significant for every update in Table A. UQAS already has a lower mean attack AUC than the baseline at 4 steps. The AUC reduction from 4 to 64 steps is also larger for UQAS. With masked fine tuning, the attack AUC is also lower for the UQAS architectures. Across architectures, lower TV corresponds to lower attack AUC after unlearning. These results link lower TV to reduced membership leakage and support its use for evaluating unlearning. We will add these results and the complete membership inference audit to the revised version.
To W2: Thank you for this suggestion. Our circuit widths follow common practice in QML, where circuits of up to 10 qubits are a standard setting. For example, QuantumDARTS uses 8 qubits for classification [5] and QuACK uses 10 qubits [6]. QDEQ uses 4 and 10 qubits [7]. Following your suggestion, we have extended our experiments to 12 and 14 qubits (Table B). UQAS-Select lowers the mean TV over the four tasks from 0.4174 to 0.1299 at 12 qubits and from 0.3038 to 0.1007 at 14 qubits. At 12 qubits, UQAS-Design reduces the mean TV further to 0.0786.
Table B: Mean unlearning discrepancy of UQAS-Select at 12 and 14 qubits.
Regarding task complexity, the paper includes a task on quantum data (TFIM) and a multiclass task on Digits. Select lowers the mean TV on both under all three request types (Table 2 and Table 9 of Appendix C.3). We have also extended Digits to four and five classes, where Select lowers the mean TV from 0.0879 to 0.0723 and from 0.2392 to 0.1691. In future work we will extend UQAS to larger widths and more complex tasks. We will add the complete experimental results of both extensions to the revised version.
[1] Guo et al. Certified Data Removal from Machine Learning Models. ICML 2020.
[2] Gibbs and Su. On Choosing and Bounding Probability Metrics. International Statistical Review, 2002.
[3] Hangleiter and Eisert. Computational Advantage of Quantum Random Sampling. Reviews of Modern Physics, 2023.
[4] Sarmasarkar et al. Auditing of Unlearning Algorithms. arXiv:2607.05898, 2026.
[5] Wu et al. QuantumDARTS: Differentiable Quantum Architecture Search for Variational Quantum Algorithms. ICML 2023.
[6] Luo et al. QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning. NeurIPS 2023.
[7] Schleich et al. Quantum Deep Equilibrium Models. NeurIPS 2024.