- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes PRISM, a retain-free machine unlearning framework designed to reduce the computational cost of unlearning requests. It learns a structural prior from pretrained model parameters using a VAE and combines it with forget-data gradients for a single-step parameter update. Experiments show competitive unlearning performance and improved computational efficiency across discriminative and generative models.
Critical strengths
-
The paper addresses practical challenges in retain-free unlearning, particularly the computational cost of repeated optimization and forgetting-strength calibration.
-
The separation of offline structural modeling and request-time updates is interesting and allows the learned prior to be reused across different unlearning requests.
-
The experiments cover multiple unlearning tasks across discriminative and generative models, with useful ablation and efficiency analyses.
Critical weaknesses
-
Unclear structural prior construction: The paper does not sufficiently explain how the VAE learns meaningful parameter dependencies from the pretrained model, making the central component difficult to assess and reproduce.
-
Incomplete calibration cost analysis: The reported calibration times exclude the evaluation cost needed to verify whether a forgetting target has been met, potentially underestimating the practical overhead.
-
Limited evidence for concurrent requests: The experiments evaluate sequential rather than concurrent requests, and retain accuracy degrades after repeated unlearning, leaving the claimed scalability insufficiently validated.
Questions for authors
-
How does the VAE learn meaningful structural dependencies from the pretrained model's parameters?
-
Does the reported calibration time include the cost of evaluating whether the forgetting target is met?
-
How do the sequential unlearning results support the claimed efficiency of handling concurrent requests?