- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes a method for machine unlearning. It uses two proxy models to adjust an existing model’s predictions. One represents the original data. The other represents the retained data. The method automatically selects the strength of this adjustment. The authors provide theoretical analysis and evaluate class and subclass forgetting on image-classification datasets.
Critical strengths
S1. Automatic Selection of the Adjustment Strength
The method provides a concrete procedure for choosing how strongly to change the model's predictions. This addresses a practical choice that otherwise requires tuning.
S2. Comparison With Retrained Models
The evaluation compares output distributions with those of retrained models. This addresses the intended outcome of unlearning more directly than forgotten-example accuracy alone.
Critical weaknesses
M1. What does each new component add?
The paper acknowledges that earlier methods already correct predictions using auxiliary models. UCD uses two auxiliary models. T3-Unlearning also studies distribution corrections for unlearning.
The main advance therefore appears to be the joint proxy construction and automatic adjustment strength. I would like clearer evidence of what each adds. In particular, it is difficult to judge the automatic scaling without comparing adjustment strategies using the same proxies.
M2. What happens when the proxies are poor?
The correction depends on the proxies. Their behaviour when inaccurate is therefore important. Proposition 1 assumes that the retain proxy is closer to the true retain posterior than the original proxy. Algorithm 2 checks the normalisation function. It does not check this assumption. The claim that incorrect proxies lead to zero scaling therefore does not follow from this check alone. Automatic scale selection is a central contribution. I would like to see when inaccurate proxies cause the method to harm performance, and whether a practitioner could recognise these cases before applying the correction.
M3. The comparison with Datamodel Matching
Datamodel Matching uses data attribution to predict retrained outputs. It then adjusts the original model to match those predictions. This differs from fitting a density model to retained examples.
The argument that modelling only retained data is suboptimal does not establish an advantage over Datamodel Matching. The distinction needs more care. A direct comparison is needed only if the authors retain a claim of superiority.
M4. What this means for individual-data removal
The medical application I have in mind is removing a patient's contribution after their data are withdrawn. The current experiments do not establish that outcome.
Matching a retrained model's predictions is useful evidence. It does not, by itself, establish protection against privacy attacks. The paper acknowledges this distinction, but it should remain clear when discussing the practical guarantees. This requires narrower wording, not a medical benchmark.
Questions for authors
Post-rebuttal update — Weak acceptance. (editing to make it more structured)
Thank you for the substantial revisions. I am raising my rating to weak acceptance.
--The matched-proxy experiments and expanded Datamodel Matching discussion meaningfully address M1 and M3, and the new robustness experiments strengthen the evidence for adaptive scaling.
--My remaining concern is the interpretation of the guarantee (M2): the retained-data diagnostic does not verify the full theoretical condition. Please distinguish this empirical safeguard from the CONDITIONAL guarantee, and describe zero scaling as abstaining from unlearning. I think that the paper should have "conditional guarantees" qualified throughout. I am on the fence for whether this should be in the title but err on no.
--For M4, please keep the distribution-level scope explicit in the main claims. Individual-example privacy guarantees are not required for this contribution.
Original questions and assessment (before rebuttal):
- M1: Identify which results isolate the benefits of joint proxy construction and automatic scaling. If this is not already tested, a matched comparison of adjustment strategies using the same proxies would help.
- M2: Distinguish the conditional guarantee from what the implemented procedure can verify. Revise the safety claims accordingly. A small sensitivity experiment with inaccurate proxies would help. A general failure-detection method is not required. State whether harmful updates can be recognised before use.
- M3: Clarify the distinction from Datamodel Matching. Support any claim of superiority with a direct comparison, or narrow the claim.
- M4: State what the evaluation establishes about forgetting. Separate this from what remains untested about individual-data removal and privacy.
M1 and M2 were my main reasons for weak rejection before the rebuttal. The updated assessment above supersedes that recommendation.
5 comments
Dear Reviewer,
Please do not let us down. We have devoted a great deal of time and effort to revising the submission. We dare think that this new version meets your expectations.
Regards
Hi all,
Thank you and congratulations for the substantial work. I can imagine you burning the midnight oil, similar to our team to ensure the questions were addressed.
I am upping this to a weak accept. "accept" because the work is a solid effort to carefully describe the concept with appropriate experimentation and ablations.
"weak" because it is not have a clear practical application. --The guarantees are still quite conditional and narrow. --The positioning within existing literature is a bit weak --The methodological advance is incremental (not bad just a bit small)
Do you think you can better distinguish the work from existing output-correction approaches?
We thank the reviewer for their detailed and insightful comments, leading to targeted revisions (in blue) in the manuscript.
M1. What does each component add?
First, we thought that Fig. 2 (right) sufficiently illustrates the crucial role of the automatic scaling. It shows the trajectory of the unlearned model qη when the scaling η increases starting from 0. This trajectory is pictured in terms of proximity (measured with empirical Kullback-Leibler divergences) to the ideal model (x-axis) and the initial models (y-axis).
We emphasize this more in the revision:
We now mark the point on the trajectory at η=1 with a red circle and add a comment in the revised version.
Second, in relation to your comments M2 and M3, the new App. G.2 proposes a new experiment with the proxies proposed in the Datamodel matching paper plus our adaptive scaling. In short, adaptive scaling becomes more essential whenever the proxies are inaccurate.
Finally, regarding the joint proxy construction, we emphasize it more in the text. We explain the interest of the 2C construction (i) for efficiency purposes (a single fit) and (ii) for focusing on the modeling shift (Prop.2 and Prop.3).
M2. What happens when the proxies are poor?
You are absolutely right. We added Appendix D to address your concern, as well as in the ETAMAX procedure (Alg. 2) in this sense.
We propose a detection of those cases. After identifying the proxies, the practitioner computes this estimator on a held-out validation set of retained data. The new App. D.1 explains how this estimator works. Note that this test is now integrated into Alg. 2 (ETAMAX): If the test fails, ηmax is set to 0.
A new experiment in App. D.2 considers several proxies for pr learned with less and less data. This artificially makes the assumption less likely to hold. It shows that the new estimator yields little to no undetected violation.
Also, we used undertrained datamodels to create inaccurate proxies in App. G.2. Their use for unlearning is detrimental when used without scaling (ie. η=1). Our automatic scaling succeeds in limiting this effect.
M3. The comparison with Datamodel Matching
The way we cited this paper was very confusing. This work deserves much more attention, and we develop Appendix G in this sense.
M4. What this means for individual-data removal
We agree. Be it the behavioral guarantees (main propositions) or the application to privacy auditing (see App. I), our results concern only averaged statistics. For instance, App. I estimates the difficulty for an attacker to distinguish the unlearned model from an ideal retrained model that never saw the forget data, on average, ie. over typical data. This doesn't mean that the attacker fail on a non-typical data sample. We clearly do not have any individual sample guarantees. This is clearly stated in App. I.2.
Of note, we consider scenarios (subclass and class) where the forget data are correlated because they share the same semantics. Our work focus more on unlearning this specific meaning: a distribution and not a specific example. The original verbatim DMM, for instance, cannot by design handle this kind of scenario (see App. G.2).