- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies client-level machine unlearning in graph federated learning. After a client withdraws and requests deletion of its data, its influence may remain in the shared model. The authors propose FedGCV, which consists of two main modules: first, gradient correction adjusts the unlearning update of the target client so as to minimize harm to the performance on retained data; second, the virtual client uses spectral information, feature statistics, and a VGAE to generate synthetic subgraphs to compensate for the loss of graph topology and model performance after deleting the client. Experiments use accuracy and MIA rate as metrics, compare with multiple federated unlearning baselines, and show that FedGCV achieves the best utility–unlearning trade-off among non-retraining baselines.
Critical strengths
The paper addresses a problem with clear research value. Since GNNs aggregate information from neighboring nodes through message passing, client-level deletion may affect the representations and predictive performance of retained clients. Therefore, compared with deleting independent samples in standard federated learning, unlearning in graph federated learning is subject to more complex structural dependencies. The two modules proposed by the authors correspond to two issues in the unlearning process: gradient correction is designed to reduce the harm caused by the unlearning update to the performance of retained clients, while the virtual client aims to compensate for the loss of graph structure and model utility caused by deleting the client subgraph. Under the four datasets and evaluation protocol reported in the paper, FedGCV achieves the highest accuracy and the lowest MIA rate among non-retraining methods, indicating a favorable utility–unlearning trade-off in this experimental setting.
Critical weaknesses
- The evidence provided for the paper's stronger claims about privacy preservation and thorough unlearning is still insufficient. Virtual-client artifacts may retain information from the client to be forgotten, limiting the interpretation to model-level empirical forgetting if these artifacts are retained. Moreover, the reported MIA results do not establish privacy against attacks on these artifacts. In addition, the implementation settings explicitly describe optimization against a fixed pre-unlearning loss threshold, while MAIT reuses the same threshold for evaluation. Therefore, the lower MIA rate may partly reflect optimization tailored to this specific attack protocol and does not by itself substantiate the stronger claim of thorough unlearning.
- The core idea of gradient correction is conceptually related to existing projection-based or conflict-aware federated unlearning methods. It is suggested to further clarify its methodological differences and graph-specific contribution. Although Figure 1 provides component ablations, these do not establish the added value of the proposed correction over existing alternatives with the virtual-client module held fixed. This leaves the additional contribution of the gradient-correction mechanism insufficiently established.
Questions for authors
- What is the deletion scope of the virtual-client artifacts? Specifically, are the spectral information, feature statistics, VGAE-derived information, and synthetic subgraphs generated from the client to be forgotten considered part of the deletion request? If they are retained, how should the paper's claims about privacy preservation and thorough unlearning be interpreted?
- How does the proposed gradient-correction method differ from existing projection-based federated unlearning methods? In particular, what graph-specific property requires the proposed correction, and how much of the reported improvement comes from gradient correction itself rather than from combining an existing unlearning update with the virtual-client module?
2 comments
Thank you for the detailed response. The proposed experiments and analyses address several of my concerns. I will retain my current rating.
We sincerely thank Reviewer q4ZV for the insightful comments and for acknowledging the importance of addressing structural dependencies in GFU. To address your concerns, we have scoped all claims in the revised manuscript to model-level empirical unlearning, added threshold-free Loss-AUC and λm=0 evaluations, and conducted controlled ablations comparing our gradient correction against FedOSD-proj and FedCARE-proj with the virtual client held fixed.
We have revised the manuscript throughout (Abstract, Sections 1, 3.2, 4.2, and 5) to state explicitly that FedGCV targets model-level empirical unlearning under a bounded client handoff. Target-derived artifacts (Δu and (Asyn,Xsyn,Ysyn)) are used transiently on the server for Rv=5 recovery rounds and purged immediately afterward. If a deletion request forbids any derived artifacts, they are discarded immediately and recovery relies solely on retained clients.
To verify that low MAIT does not merely reflect optimization against the shared cutoff τpre (λm=3.0), we evaluate both λm=0 and an independently calibrated, threshold-free Loss-AUC MIA on Cora and CiteSeer:
Across both datasets, FedGCV (λm=0) already reduces MAIT to 7.92%–10.46%, and FedGCV's threshold-free Loss-AUC (52.14%–53.82%) stays close to the ~50% random-guess baseline of Retrain (49.72%–50.21%), confirming genuine empirical forgetting independent of τpre.
FedGCV differs from existing projection methods in two ways: (1) It projects onto a single aggregate half-space {d:⟨d,Δr⟩≥0} rather than enforcing strict per-client orthogonality (which over-constrains non-IID graphs as in FedOSD). This preserves a larger feasible descent region so unlearning updates are not overly attenuated by conflicting client directions—preventing incomplete forgetting (e.g., FedOSD's 29.63%–29.84% MIA on Cora/CiteSeer)—while keeping server projection O(d) and independent of client count M. (2) It obtains the conflict reference directly from retained clients' GNN updates over observed neighborhoods rather than server-synthesized Euclidean pseudo-samples (FedCARE). This directly captures multi-hop message-passing dependencies rather than isolated out-of-manifold pseudo-samples, preserving retained graph utility while reusing existing FedAvg updates at zero extra generation or communication cost.
In Figure 1, the
w/o GRU(without gradient correction) baseline already keeps the virtual client enabled, showing that gradient correction reduces Cora MIA from 24.07% to 5.56%. To strictly isolate the projection rule itself, we hold the virtual-client recovery module fixed and compare alternative correction rules below:With VC fixed, replacing our gradient correction with FedOSD-proj or FedCARE-proj drops accuracy by 8.4–13.7% and leaves higher MIA, isolating the direct contribution of FedGCV's neighborhood-aggregated half-space projection.
We hope these revisions and controlled experiments clearly define the artifact deletion scope, confirm that forgetting is independent of the fixed cutoff τpre, and isolate the contribution of our gradient correction module. Please let us know if any points warrant further clarification.