- Rating
- 3(+1)
- Confidence
- 3(−1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies federated unlearning when the model has persistent copies, such as personalized adapters, offline clients and released checkpoints. The authors argue that current methods only edit the server's global model, so uncorrected copies keep the withdrawn content and can bring it back through later aggregation. Thus, they propose LOCUS, which has three stages. (1) Influence Localization has each holder report local readings to decide which copies need correction. (2) Correction Propagation sends one minimum-norm correction to all of them and blocks uploads from holders that haven't acknowledged it. (3) Divided Verification combines the removal, retention and acknowledgment checks into one certificate. Experiments on TOFU and MUSE-News with 20 clients show that LOCUS corrects 92% to 99% of the affected copies and keeps the erasure through 300 rounds of continued training, while server-side unlearning corrects none.
Critical strengths
-
The problem is important and under-explored. The paper makes a good point that federated training leaves copies everywhere, and that editing only the server model misses them. Figure 2 shows that uncorrected copies can bring the forgotten content back within a few rounds. Table 9 suggests that very few existing protocols deal with this.
-
The idea of running each step where its evidence lives is intuitive. The acknowledgment gate is simple but effective, and the ablation in Table 2 shows that each of the three stages matters.
-
The experiments are extensive. The paper covers five unlearning objectives, seven federated unlearning protocols, three deployments and a 300-round continuation. It also includes broadcast and retraining controls, sequential requests, adversarial reflow, and different model families and client counts.
-
The paper is open about its limits. It reports how much the localization step leaks (Table 7) and where forged acknowledgments break the certificate (Table 4).
-
The figures and tables are clear and nicely designed. At a time when many papers feel rushed, I can see the care the authors put into their figures and tables, and I really learned a lot from them.
Critical weaknesses
-
I am worried that a simple control may nearly match LOCUS. Broadcast-all with the same gate reaches full coverage on all three deployments and also survives 300 rounds, using 40 messages against 41 for LOCUS (Tables 1 and 5). The main gain of LOCUS is lower retention excess and slightly higher utility. Meanwhile, the headline numbers mainly compare against methods that were never designed to touch the copies, and server-side coverage is zero by construction. So the value of localization may be smaller than the abstract suggests.
-
The method relies on retrained references. The thresholds and the retention baselines come from matched leave-requester-out retraining for every copy class. However, the paper doesn't explain how they are obtained in practice, and their cost isn't counted in Table 5.
-
The theory does not fully support the claims. Theorem 4 is a linear extrapolation that assumes a positive descent rate at every round. Theorems 8 and 11 show that the server can't know what it never receives, which is rather intuitive. None of the results gives a formal unlearning guarantee for the corrected copies, and the certificate is essentially a set of measured loss thresholds.
-
The experimental setup is relatively small. By default, the paper uses 20 clients, a single request and rank-16 adapters, and each 7B deployment is run only once.
-
This paper introduces too many new terms (e.g., carriage reading, participation closure, governed copies, reflow, release margin), and the abstract is hard to follow on a first read. I suggest the authors polish the writing in a later version.
Questions for authors
I would be thankful and willing to raise my score if the authors can (partly) address the following questions/concerns.
-
Is the benefit over Broadcast-all with the gate only in retention excess? Could the authors show a setting where broadcasting to everyone causes a clear utility loss and localization really matters. For example, with many more clients or a larger retention cost?
-
How are and the retention baselines obtained without retraining? How do results change when the thresholds are estimated from a proxy instead of a matched reference?
-
What happens with a dishonest client that forges its acknowledgment or sends restoring updates after acknowledging?
-
Can the copy probe be made mandatory, and what does it cost?
-
Could the authors report results with more clients?