- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies blind federated unlearning, where the target client may be unavailable from the outset or depart before unlearning is complete. In the paper, the authors propose NoPE, which combines server-side training on class-conditioned random noise with retained-client updates.
Critical strengths
- The paper consider an understandable and practical research question, where the unlearning client can not participate during the unlearning phase.
- The method does not require client data for the unlearning phase.
Critical weaknesses
- The paper presentation require significant improvement.
- Although current related works have been investigated widely, parts of them are not yet peer-reviewed or does not from flagship venues like CVPR, NeurIPS, ICLR or ICML. Another speaking, it would be good if the literature reviews should be much more carefully considered. More specifically, more works in recent flagship venues should be investigated.
- One of my biggest concerns lay in the utilization of the mean and standard deviation of the input data for the augmentation. It is not well proven of how it can work. A comprehensive experimental evaluations and other visualization and analysis should be made to prove this claim. The paper can consider the literature reviews in this type of approach to indirectly improve the soundness of the paper.
- Beside the utilization of mean and standard deviation of the input data, NoPE combines training on a proxy task with recovery on retained data. This simplicity is somehow good, but the current evidence does not establish why the procedure removes the target client’s influence specifically. The noise proxy depends on the target client only through its dataset size and aggregation weight, so the server would inject the same signal whichever client requested unlearning.
- According to the experimental evaluations, the current manuscript should consider a more challenging dataset and more baselines in 2025 and 2026 to prove the method better.
Questions for authors
- What is the difference between prototype and mean of the data in the paper?
- As in the T-SNE figure, the clean and noisy data according to different class are not correlated. How do we achieve the generalized unlearning performance on the clean dataset when we apply it on the noisy dataset? It makes me feel confused about the technicality and soundness of the paper.