- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper demonstrates from an information-theoretic perspective that "forget-only" forgetting is, in principle, sometimes impossible to achieve, and explains the reason (information loss). However, it does not prove that practical "forget-only" methods fail for this specific reason.
Critical strengths
- The motivation is clear.
- This paper demonstrates from an information-theoretic perspective that "forget-only" forgetting is impossible to achieve
- The permutation/chain-rule accounting is a simple and reusable way to avoid double-counting information shared between requests.
Critical weaknesses
- the same algorithm A produces both the pretrained model M = A(S) and the retraining target W = A(S∖U). The memorization results (Props. 4.4–4.7) are stated as “any forget-only unlearner satisfying the assumptions must obey I(M; S) ≥ …”. Yet for the bare learner, I(M; S) is log q or 0, which is far below the bound. The propositions therefore say that no such unlearner exists for this A. That makes them a second impossibility result, not a memorization requirement. But,the authors further interpret them as “a successful implementation would have to store additional state.” But if A is augmented to A'(S) = (h_S, state_S), then the retraining target A'(S∖U) also changes.
- It mentions the “constructions extend to larger N” but gives no details.
- The paper is purely theoretical, with only toy examples. A small experiment showing a common forget-only method failing as predicted would make the results more convincing.
- The connection to empirical forget-only methods (gradient ascent, NPO, etc.) remains informal.
Questions for authors
- Do the authors think the failure of forget-only methods is closely related to knowledge entanglement? How does the “information loss” explanation relate to the commonly discussed “knowledge entanglement” explanation for the failure of forget-only methods?
- The examples in the paper are simple learners such as thresholds and the median. Could you give a more realistic case, for example a neural network or a language model, where this information loss happens and causes forget-only unlearning to fail?
5 comments
Gentle Reminder
We would like to gently remind the reviewer that the discussion phase is approaching its conclusion. If there are any outstanding concerns, we would be happy to address them. Otherwise, we kindly request that the reviewer consider our rebuttal when reassessing their score.
Additionally, we would like to draw the reviewer’s attention to our general comment addressed to all reviewers, titled “Clarification on the Theoretical Nature of Our Contribution,” which aims to address the shared concern regarding the absence of experiments in our work.
Final Reminder Before the Discussion Deadline
With less than 24 hours remaining before the discussion phase concludes, we would kindly ask the reviewer to consider our responses and let us know if any concerns remain unaddressed. If the reviewer finds our clarifications satisfactory, we would appreciate their consideration when reassessing the initial score. We would also like to draw attention once more to our general comment, “Clarification on the Theoretical Nature of Our Contribution.”
Thank you again for your time and feedback.
We thank the reviewer for their insightful feedback.
W1. Yes, Propositions 4.4–4.7 establish impossibility for the bare learners considered. However, they are also instances of memorization requirements: Theorem 4.3 establishes a learner-dependent necessary information condition for successful forget-only unlearning, and the propositions show that the fixed learners fail to meet it, implying impossibility. Our goal with saying "a successful implementation would have to store additional state." is to highlight that if a forget only learner were to exist, it would need to store more information than the fixed learner. We agree that it would change both the unlearning and retraining target as a result and the memorisation lower bound would need to be satisfies with those changed targets.
W2. We agree that the extension to larger N was only implicit, as we used N=2 for illustration. We did primarily for simplicity to avoid having to write down cumbersome examples. Below, we provide an explicit construction for the threshold example with N>2. Similar extensions are possible for the other examples and we will include them in the revised version.
The N=2 threshold construction achieves the maximal separation Δ=c−21. For a given 2<N≤2c, we extend it by choosing N approximately equally spaced retraining targets within the same interval, while keeping the common deletion request U=⋃j=1m{(−c+1,+1)}. Define Si=U∪{(−c,−1),(−c+ki,+1)}∪⋃j=1n−m−2{(−c,−1)}, where ki=1+(i−1)⌊(2c−1)/(N−1)⌋ for i∈[N]. Then all pretrained models coincide at A(Si)=−c+21, while the retraining targets satisfy A(Si∖U)=−c+2ki. Hence, their minimum pairwise separation is Δ=21⌊(2c−1)/(N−1)⌋>0, recovering the original construction when N=2.
W3. Our contribution is indeed theoretical, with the goal of characterizing the intrinsic difficulty of the problem rather than providing an algorithm for unlearning or experimentally evaluating unlearning. As such, our examples quantify the information necessary for any algorithm to satisfy the unlearning guarantee. However, we agree that an empirical demonstration would strengthen the results. Our preliminary decision-tree experiments support the bound: the bare learner lacks sufficient memorization, and even the optimal forget-only method fails. If the reviewer finds this useful, we will include these results in the revision.
W4. Our result provides a lower bound on the amount of information a learner needs to retain to satisfy a formal unlearning guarantee. Neither gradient ascent nor NPO provides such a guarantee in their standard formulations. Even if they did, the success of these methods would depend on whether the learner itself retained the required information and whether the unlearner could access it. As discussed, there are good reasons to explore whether the information memorized by overparameterized networks could indeed be efficiently accessed.
Q1. We thank the reviewer for the interesting question. We think knowledge entanglement and information loss in forget-only unlearning are related but distinct explanations for unlearning failures. Knowledge entanglement concerns the overlap of representations associated with different pieces of knowledge, including knowledge derived from forget and retain data, making them difficult to separate. In contrast, our information-loss explanation concerns the inability to identify the correct retraining target from the information available to the unlearner. We agree with the reviewer that if the representations were overlapping then it does make the problem of identifying the correct retraining target difficult. However, even if an algorithm could perfectly separate different pieces of knowledge, a forget-only unlearner would still need sufficient information to identify the correct retraining target; otherwise, it would face the same impossibility result. Conversely, having sufficient information to distinguish between retraining targets does not imply that an algorithm can successfully separate forget and retain knowledge. Thus, while both explanations concern the difficulty of removing forget-data influence while preserving retained knowledge, they address two distinct challenges: selective modification and identifiability, respectively.
Q2. We kindly refer the reviewer to our answer to Q1 of Reviewer CXWo. The purpose of using thresholds and medians as examples was to simply illustrate the applicability of our framework to fundamental learning problems, as commonly seen in learning theory and differential privacy literature.