- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
I am not an expert in this specific research area. I have made an effort to understand the method and evaluate the paper, but I still find some aspects difficult to assess confidently. I hope the authors and AC will also carefully consider the opinions of reviewers with more direct expertise in generative model unlearning and optimal transport.
This paper proposes UOT-Unlearn, which applies unbalanced optimal transport (UOT) to concept unlearning in pretrained one-step generative models. Compared with existing unlearning baselines, including GA, VDU, SA, and SalUn, the method achieves good unlearning performance measured by PUL while maintaining reasonable generation quality measured by u-FID. However, the paper is difficult to read, and the generation quality still degrades subs
Critical strengths
-
The paper addresses the useful problem of unlearning concepts from one-step generative models.
-
Compared with GA, VDU, SA, and SalUn, the proposed method achieves good unlearning performance while maintaining reasonable generation quality.
Critical weaknesses
-
Generation quality degradation: Although the method achieves good PUL scores, generation quality still degrades substantially compared with the pretrained model. For example, on ImageNet-256, the u-FID of MeanFlow increases from 5.52 to 8.54 after unlearning. This degradation may limit the practical usefulness of the method.
-
Unclear contribution of UOT: The paper needs to demonstrate whether the improvements genuinely come from the unbalanced optimal transport formulation, rather than mainly from the manually designed forgetting cost and class redirection strategy. The current results do not sufficiently isolate these contributions.
-
Presentation and clarity: The paper presents a relatively intuitive goal through complex optimal transport formulations, making it difficult to understand the core idea and its specific contribution.
Questions for authors
Could the authors provide the following controlled comparisons, with other settings kept as consistent as possible?
-
Full method: The proposed forgetting cost combined with UOT distribution constraints.
-
Simpler regularization: The same forgetting cost combined with a simpler distribution-preserving regularization objective instead of UOT.
-
Balanced OT: The same forgetting cost using standard OT with strict marginal constraints instead of UOT's relaxed marginal constraints. These comparisons would help establish whether the unbalanced nature of UOT is necessary for the reported improvements.
5 comments
[W3] Presentation and clarity: The paper presents a relatively intuitive goal through complex optimal transport formulations, making it difficult to understand the core idea and its specific contribution.
A. We agree that the optimal transport formulations are complex, but we believe that UOT formulation is proper to mathematically state our core idea: unlearning requires the generated distribution to deviate from the pretrained one on the forget region while keeping the other modes unchanged. As optimal transport is well-established mathematical fields, most of the existing formulation follows the recent works.
Theoretically, the forgetting cost (Eq. 16) penalizes any generated sample that still looks like the forget class, pushing it out of the forget region , which is our key idea and contribution of UOT compared to OT. Moreover, because the penalty is an -divergence, the displaced mass must be redistributed to the retain classes rather than to noise-like samples.
Empirically, the controlled comparisons in Table 4 (see [W2, Q1]) make the contribution of each part visible. With balanced OT, the marginal error is forced to zero, so PUL stays low even with the unlearning cost (52.76). With a simpler WGAN regularizer, the forgetting cost can raise PUL (72.23), but the regularizer lacks the support-confinement property, so the expelled mass is not redistributed to the retain classes and u-FID rises to 20.09. Only the forgetting cost combined with UOT achieves both high PUL (84.32) and low u-FID (8.32).
We have added the rationale of UOT and unlearning in the Section 3.2.
Dear Reviewer vPwp,
Thank you again for your constructive review. As the author–reviewer discussion period ends on November 18 (AoE), we would be grateful if you could let us know whether our responses have addressed your concerns.
On the contribution of UOT, we added the requested controlled comparisons with the same forgetting cost (Table 4): balanced OT loses about 30 points of PUL (52.76 vs. 84.32), and the simpler WGAN-GP regularizer more than doubles u-FID (20.09 vs. 8.32). On the quality degradation, we clarified that the u-FID increase from 5.52 to 8.54 on ImageNet-256 is obtained at 98.75% PUL and is the smallest among all compared methods, where the next best baseline reaches 12.70 at only 61.29% PUL. On the clarity, we added the rationale for the UOT formulation to Section 3.2. We have also revised the paper accordingly. We would be happy to clarify any remaining questions.
A. The increase from 5.52 to 8.54 is obtained at 98.75% PUL, i.e., near-complete erasure of the forget class, and it is the smallest degradation among all compared methods by a wide margin: the next best baseline on ImageNet-256 reaches u-FID 12.70 at only 61.29% PUL (SA), and the others exceed 49. Some loss of fidelity is inherent to unlearning, since the generator must leave the pretrained distribution on the forget region, and a trade-off between PUL and u-FID is observed for every method in Fig. 3. What distinguishes our method is the shape of this trade-off: the baselines' u-FID rises sharply once PUL becomes meaningful, whereas ours stays nearly flat, so a few FID points buy almost complete erasure. In practice, the practitioner can choose the operating point on this trade-off. A practitioner who prefers higher fidelity can simply stop earlier along the trajectory in Fig. 3. Even at such an earlier point, our method still achieves higher PUL than the baselines at the same u-FID.
A. Following the reviewer's suggestion, we added the requested controlled comparisons with all other settings kept fixed: (2) a simpler regularization variant that combines the same forgetting cost with a WGAN-GP objective (WGAN + cul; we also report WGAN w/o cul as a reference without the forgetting cost), and (3) a balanced OT variant that uses the same forgetting cost with standard OT under strict marginal constraints (OT + cul), alongside (1) our full method. The results, reported in Table 4 of the revised manuscript, show that the UOT formulation is necessary for the reported improvements: WGAN + cul retains moderate PUL but more than doubles u-FID (20.09 vs. 8.32), while balanced OT + cul loses about 30 points of PUL at comparable u-FID (52.76 vs. 84.32).
We discuss why these three outcomes follow from the structure of the UOT objective in our response to [W3] below.