- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies machine unlearning when forget-set membership is uncertain and represented by continuous sample-wise likelihoods. The proposed UADU framework first constructs likelihood-conditioned training-label targets using retention-weighted reference predictions and projected feature similarities. It then redistributes non-label probability mass through entropy-constrained optimization and fits the resulting targets. Experiments cover mislabeled-data removal on three image-classification datasets, with additional detector, architecture, and backdoor evaluations.
Critical strengths
- UADU achieves forget accuracy closer to Retrain than the reported baselines across the three main datasets, with complementary membership-inference measurements.
- The paper includes component ablations and sensitivity experiments.
Critical weaknesses
- Figure 1 looks AI-generated. I recommend redrawing it with a clearer and more consistent technical presentation.
- The related-work discussion should include relevant recent studies, including those published at CVPR 2026. Additional comparisons with these methods would help establish the contribution.
- Can UADU be extended to unlearning in generative models? Please discuss its applicability and the modifications required, particularly given its reliance on class probabilities and a linear classification head.
- In Section 5.1, conventional baselines receive thresholded forget/retain assignments, whereas UADU uses continuous forgetting likelihoods. The threshold sweep in Appendix C.3 does not resolve this difference. Comparisons with softly weighted baselines using the same likelihoods are needed to isolate the benefit of the proposed distributional formulation.
Questions for authors
see weakness
We sincerely thank the reviewer for their careful reading and attention to detail. Please find our response below. (W for weakness, Q for Questions) Revisions are marked in blue in the updated PDF, locations follow each reply.
1. Clarity and Consistency of Figure 1 [W1]
We have redrawn Figure 1 to provide a clearer and more consistent technical presentation. The revised Figure 1 is available at the provided link and is included in the revised manuscript.
https://drive.proton.me/urls/W1GX06FEP8#OqcjhF7J0ssO
The revised figure simplifies the visual design and more explicitly shows the computational flow of UADU, including projected reference similarity, retention-weighted aggregation, the likelihood-conditioned objective, and the subsequent entropy-constrained redistribution and target fitting.
Revision: Figure 1.
2. Recent Related Work and Additional Comparisons [W2]
We thank the reviewer for this suggestion. Among recent CVPR 2026 unlearning studies, few address instance-level unlearning with publicly available code. We therefore compare MUpHT [1], which satisfies both conditions and enables a reproducible evaluation. We follow the authors' official implementation and reported main parameter settings.
At comparable retain accuracy, UADU achieves substantially lower Af than MUpHT across all three datasets. Its MIA is also consistently closer to Retrain. These results support the effectiveness of UADU relative to a recent CVPR 2026 instance-level unlearning method.
Revision: Sections 2.1 and 5.1--5.2 (Table 1).
3. Applicability to Generative Models [W3]
UADU can be adapted to autoregressive generative models, which predict a categorical distribution through a softmax head. In this case, next-token probabilities replace class probabilities, and the observed next token serves as the training label. LCUO can construct token-level targets from references with similar hidden representations, using the observed token’s output-head weight as the projection direction. ECDO can then preserve the prescribed token probability while redistributing the remaining vocabulary mass under the same entropy criterion. We will discuss this extension in the revised manuscript.
Revision: Section 6.
4. Comparison with Softly Weighted Baselines [W4]
We agree that the threshold sweep in Appendix C.3 varies only the hard retain–forget assignments and therefore does not isolate the effect of using continuous forgetting likelihoods. We accordingly add two baselines that use the same pi as UADU. Soft-weighted Losses weights standard retain-loss minimization and forget-loss maximization by 1−pi and pi, respectively. Direct Distillation directly fits reference-based soft targets obtained by combining original and reference predictions according to the forgetting likelihoods. Both baselines use the same original models and forgetting likelihoods as UADU. We follow their core training settings, where applicable, and compare at similar mean retain accuracy.
At comparable mean retain accuracy, UADU achieves the Af closest to Retrain across all three datasets. Its MIA is also closest to Retrain except against Soft-weighted Losses on TinyImageNet. These results show that UADU's gains are not explained by access to continuous likelihoods alone, supporting the benefit of its target construction and distributional optimization.
Revision: Appendix C.6.
[1] : Qian, Chengyao, et al. "pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026.