- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes RePASTA-CU, a pair of learning-unlearning algorithms using non-private training and PASTA updates. The algorithms allow for deletion of training samples and update of the model by using a checkpoint of the initial learning algorithm. The authors establish that the proposed RePASTA-CU is certified unlearning, removing the assumptions of bounded gradient oracles, smoothness Lipschitz continuity and weak-convexity of prior literature. They provide also a utility bound under weak convexity and quadratic growth condition on the subgradients, establishing a RMS rate before publishing noise injection is conducted. Experiments across different datasets compare the proposed method with other common baselines on unlearning.
Critical strengths
- The proposed method is shown to be certified unlearning without the assumptions of bounded gradient oracles, smoothness Lipschitz continuity and weak-convexity of prior literature.
- Under additional assumptions a rate is established on the RMS before publishing noise is added.
- The proposed unlearning method seems to perform a deletion and update of the model significantly fast with respect to an alternative being retraining on the retained dataset.
Critical weaknesses
- The paper is difficult to parse and there are few places where notation is not defined, making it difficult for the reader to follow. More specifically,
- in line 86 condition (7) is referenced even though define only later, breaking the pace of the presentation.
- In line 132, m is not prior defined
- In line 142, M is not defined
- In lines 149-150, G is not defined.
I think a proper rewriting of the paper will improve significantly the presentation and will highlight the contributions.
- A rate of for the RMS before publishing noise injection is established in the paper. However, there is no comparison with any rates that might exist in prior results so that the reader can appreciate the corresponding contribution. In general, comparison of the established results with the literature is largely lacking in the paper.
- The established algorithm does not seem to perform better in all the experiments than prior baselines. More specifically, in Table 1 the method performs better only in the AG News task. I would expect a proper comparison and description of why is that motivating better the use of the algorithm in practice.
Questions for authors
Can you please define the aforementioned in Weaknesses constants? Can you please elaborate on the performance of the method with respect to other prior state-of-the-art baselines?