- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2(+1)
- Presentation
- 2(−1)
- Soundness
- 2
Read review
Paper summary
The paper proposes FedRUn, a federated unlearning framework that maximizes the entropy on forget data at requesting clients. Clients return locally computed updates for server-side application, avoiding historical-update storage and additional participation from non-requesting clients.
Critical strengths
Strengths:
- The method cover a wide range of unlearning type, including the client-, sample-, and class-level unlearning.
- The method show a knowledgeable improvement in terms of computation and communication efficiency.
Critical weaknesses
Weaknesses:
-
The literature of the paper from recent years seems to be limited, thus, limiting the novelty and significance claim of the paper and the research questions. For instance, in the introduction, the paper claimed that current methods still depend on historical states, repeated recovery rounds, or method-specific assumptions. However, there are recent works in 2025-2026 (e.g., R1, R2, R3, R4, R5) already tackles these issues. A better statements and literature should be made and discussed to improve the paper significance. Also, as the baselines seem to be old, it would be good if the authors consider some literature from recent years.
- R1: Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter, CVPR 2025. - R2: NoT: Federated Unlearning via Weight Negation, CVPR 2025. - R3: Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression, CVPR 2026. - R4: Efficient and Effective Federated Unlearning via Adaptive Data Partitioning, TKDE 2026. - R5: Forgettable federated linear learning with certified data unlearning, TNNLS 2026. -
The contribution of maximize the entropy of the prediction on the TA, FA in tables 1, 8, 9 seem not to be significant over other recent works.
-
Many parts in the paper lack consistency and coherence.
-
The method seems to be incremental. The entropy maximization for the forgetting loss seems not to be a novel contribution. Many methods, especially series of gradient ascent, have used it widely [R6, R7, R8]. Meanwhile, the proximal loss appear in FedProx [R9].
- R6: A Closer Look at Machine Unlearning for Large Language Models, ICLR 2025. - R7: Certifying the Right to Be Forgotten: Primal–Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning, IEEE TIFS. - R8: Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning, ACL 2026. - R9: Federated Optimization in Heterogeneous Networks
Questions for authors
- What do you mean "these methods still depend on historical states, repeated recovery rounds, or method-specific assumptions"?
- Why Fast-FedUL contribute no unlearning computation on the client side, no storage cost and no communication cost? Why do the reported communication cost in Fast-FedUL in table 11 is reported with 446.69 MB, and in table 12, the Fast-FedUL is reported with 10710 MB?