- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies why information about a departed party can remain recoverable after retraining in vertical federated learning. The authors propose CLEAVE, which combines coordinated local edits with refitting of the prediction layer. It provides theoretical guarantees for a family of linear reconstruction models and evaluates how well the method reduces recoverable information while maintaining prediction accuracy.
Critical strengths
-
The problem and method are well motivated. The paper distinguishes between removing a party's contribution to training and reducing the information that can be recovered from correlated data held by other parties. For linear reconstruction models, the analysis tries to separate information connected to the prediction task from additional information that can be recovered. It also studies the constraints introduced by requiring each party to edit only its own representation.
-
The experiments cover three datasets and different types of deletion, and compare against retraining and existing unlearning methods.
Critical weaknesses
-
The usefulness of the certificate in practice needs clearer evidence. The paper provides a theoretical guarantee; however, the confidence intervals used in the empirical audits rely on bootstrap resampling. There is no information about the numerical error terms needed to show that the theorem gives a useful bound for the main experiments.
-
The comparison at similar prediction accuracy could be clearer. The paper also includes tests with more flexible reconstruction models. However, it does not compare CLEAVE with other federated unlearning methods under the same models. It would be good to see how CLEAVE performs there.
Questions for authors
-
The certificate in practice: For one experiment, could the authors calculate the theoretical bound using the actual audit sample size and error terms? Does it give a useful upper limit on recoverable information, and which reported results are covered by that guarantee?
-
Comparison with other methods: Could the authors extend the existing comparisons to evaluate CLEAVE, retraining, and representative federated unlearning methods using the same nonlinear reconstruction model and at similar prediction accuracy? How much of CLEAVE's reported advantage remains?