- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes FedSuCo to address the lack of global structural information in federated graph clustering. Each client first learns node representations in a Riemannian space and constructs supernodes through geometric renormalization. The framework then uses secure aggregation to collect cross-client supernode connectivity statistics and build a global weighted hypergraph. The resulting structural information is sent back to clients to support local clustering. Finally, clustering is performed using federated spherical K-means or a von Mises–Fisher mixture model. Experiments on five real-world graph datasets show that FedSuCo outperforms thirteen federated baselines in ACC, NMI, ARI, and Macro-F1.
Critical strengths
-
This paper addresses the lack of cross-client structural information in federated graph clustering. Unlike existing methods that rely mainly on model parameter aggregation, it uses supernodes to capture cross-client structural relationships. This is a meaningful approach.
-
The proposed method achieves good clustering performance on five graph datasets. The experiments also examine the effects of client number, supernode scale, and structural feedback. The paper further discusses the trade-off between communication overhead and privacy protection.
Critical weaknesses
-
Riemannian geometry-guided supernode construction is a main contribution of this paper. However, the experiments only study the effect of supernode scale. It remains unclear whether Riemannian geometry itself brings performance gains. The authors should compare it with random grouping, Euclidean clustering, and embedding similarity-based construction under the same number of supernodes and training settings.
-
FedPAM and FedNCN are discussed in the related work but are missing from the experiments. The current baselines do not sufficiently cover federated graph clustering methods. In addition, FedSuCo uses cross-client connectivity information, while most baselines do not. This makes it difficult to determine whether the gains come from the proposed method or the additional structural information. The authors should include FedPAM and FedNCN and compare methods under the same cross-client structural information.
Questions for authors
-
How much performance gain does the proposed Riemannian geometry-guided construction strategy provide over random grouping, Euclidean clustering, and node-embedding-based supernode construction?
-
Why were relevant federated graph clustering methods, such as FedPAM and FedNCN, not included in the comparison? Does FedSuCo still outperform existing methods when cross-client structural information is kept consistent?
-
Why does CiteSeer perform better in Table 3 when global structural feedback is removed? Could the feedback strength be adjusted according to structural differences across clients?
-
What are the total communication costs and end-to-end execution time of the secure computation protocols in a real multi-server setting? How do these results compare with those from trusted simulations?
-
The privacy mechanism relies on strict assumptions. However, the paper provides little empirical evidence of its actual privacy protection. The risk of information leakage needs further investigation.
-
The two-server protocol assumes that the servers do not collude and that at most one server is passively compromised. However, the protection is limited by the public information and authorized outputs. Servers can still access supernode representations, scale information, and aggregated connection statistics. These statistics may still expose sensitive information. In particular, attribute inference and membership inference attacks remain possible, even without direct access to individual node representations.
-
The construction of cross-client edge statistics assumes that both endpoint clients hold the corresponding connection records. This assumption may not hold in all federated learning settings and could limit practical applicability.
-
The authors should further evaluate privacy risks through attribute inference and membership inference attacks based on publicly available supernode statistics.
9 comments
W2 & Q2: Comparisons with directly relevant baselines are insufficient, and the contributions of cross-client structural information and model design remain unclear.
We thank the reviewer for the insightful suggestions to include directly relevant baselines such as FedPAM [1] and FedNCN [2], and to evaluate our method with cross-client structural information held constant. These insights help us distinguish the contributions of additional structural information and model design. Following your suggestions, we have added comparisons with both methods and controlled experiments assessing the role of true cross-client connectivity and the gains from server learning given the same connectivity information.
Comparison with FedPAM/FedNCN. During the original experiments, we had not obtained public implementations of these methods or received replies to our inquiries to the authors. We have now reimplemented both methods based on their papers and evaluated them on five datasets with 10 clients and five training seeds, using the same partition files as FedSuCo.
The table reports ACC and NMI (%) as mean±sample standard deviation. FedPAM and FedNCN results are from our reimplementations; FedSuCo uses vMF clustering throughout.
| Dataset | FedNCN ACC | FedNCN NMI | FedPAM ACC | FedPAM NMI | FedSuCo-vMF ACC | FedSuCo-vMF NMI |
|---|---|---|---|---|---|---|
| Cora | 24.74±2.17 | 8.35±3.58 | 29.74±0.11 | 2.22±0.23 | 74.13±1.89 | 56.20±1.64 |
| CiteSeer | 29.13±2.66 | 8.52±2.72 | 21.18±0.17 | 0.70±0.25 | 58.77±2.59 | 32.45±1.64 |
| PubMed | 41.96±3.53 | 3.70±2.28 | 54.05±6.68 | 16.85±4.91 | 64.69±1.34 | 23.68±1.27 |
| Amazon Photo | 21.73±2.19 | 6.06±1.91 | 25.36±0.02 | 0.16±0.00 | 64.61±8.70 | 58.71±6.80 |
| Amazon Computers | 19.43±2.57 | 6.02±1.62 | 37.49±0.01 | 0.12±0.01 | 40.19±4.32 | 41.32±2.57 |
Under these settings, FedSuCo-vMF achieves higher mean ACC and NMI than both reimplementations on all five datasets.
Comparison of structural information and server design. To distinguish the contributions of additional structural information and model design, we compare three variants:
- Full: Uses true cross-client edges to construct a global weighted supernode graph and trains a weighted graph encoder through link reconstruction and directional constraints to learn supernode feedback directions.
- No-cross: Retains Full’s server learning and feedback procedures but uses only intra-client edges to construct the coarse graph. True cross-client edges are never accessed, and unknown cross-client node pairs are masked out of the structural loss.
- Simple-global: Uses the same true cross-client edge information as Full but generates feedback through a fixed rule: compute a weighted average of neighboring and self directions using the current superedge weights, add it to the original direction, and normalize. No graph encoder is trained to generate feedback directions.
All three variants start from the same local pretrained models and initial supernode groups and use the same rules for assignment updates, local training, client feedback, and final clustering. Simple-global’s graph and directions still evolve during training; only its server computation rule is fixed. Thus, Full versus No-cross evaluates the contribution of cross-client edge information, while Full versus Simple-global compares server feedback designs given the same cross-client edge information.
Experiments use 10 clients, five training seeds, and vMF clustering throughout, which is shown in the following table.
| Dataset | Metric | Full | No-cross | Simple-global |
|---|---|---|---|---|
| Cora | ACC | 72.35±5.49 | 42.14±3.36 | 47.06±4.18 |
| Cora | NMI | 55.94±1.93 | 26.56±3.63 | 28.07±2.51 |
| CiteSeer | ACC | 58.77±2.59 | 52.34±4.99 | 57.05±2.99 |
| CiteSeer | NMI | 32.45±1.64 | 27.07±3.18 | 30.84±1.51 |
| PubMed | ACC | 64.69±1.34 | 56.51±2.88 | — |
| PubMed | NMI | 23.68±1.27 | 17.46±1.77 | — |
| Amazon Photo | ACC | 64.61±8.70 | 60.64±9.65 | — |
| Amazon Photo | NMI | 58.71±6.80 | 53.91±6.23 | — |
| Amazon Computers | ACC | 40.19±4.32 | 36.37±5.92 | — |
| Amazon Computers | NMI | 41.32±2.57 | 34.31±6.29 | — |
Full achieves higher mean ACC and NMI than No-cross on all five datasets, supporting the contribution of true cross-client connectivity. Furthermore, with the same cross-client edge information, Full outperforms Simple-global on Cora and CiteSeer by 25.29 and 1.72 percentage points in ACC, and 27.87 and 1.61 percentage points in NMI, respectively. These results support the contribution of the trainable server feedback mechanism beyond access to additional structural information on these two datasets.
[1] Fu et al. Unsupervised Federated Graph Learning. NeurIPS 2025.
[2] Liu et al. Federated Node-Level Clustering Network with Cross-Subgraph Link Mending. ICML 2025.
Thanks!
Thank you for your detailed responses and additional experiments. I appreciate the authors' efforts to address my concerns, particularly the inclusion of alternative supernode construction strategies, additional baselines, and controlled experiments on cross-client structural information.
These results help strengthen the empirical evaluation. However, I still have some concerns. First, the comparisons in W1 modify multiple components simultaneously, making it difficult to isolate the specific contribution of Riemannian geometry-guided supernode construction. Second, the relatively low performance of the reimplemented FedPAM and FedNCN baselines would benefit from further validation. Additionally, the comparison with Simple-global is limited to two datasets.
More importantly, my remaining questions regarding practical communication costs, privacy risks, and the assumptions underlying cross-client connectivity have not yet been addressed in the provided responses.
I appreciate the substantial additional effort and look forward to further clarification before reconsidering my rating.
Dear Reviewer ATb9,
We sincerely thank you for your careful review and insightful suggestions.
W1 & Q1: The contribution of Riemannian geometry has not been sufficiently validated against alternative supernode construction strategies.
We thank the reviewer for the suggestion. Following your recommendation, we have added comparisons with random grouping, Euclidean-distance grouping, and grouping based on the cosine similarity of learned embeddings.
Comparison settings. To evaluate FedSuCo’s overall geometric design, we construct three Euclidean baselines by replacing its coupled geometric representation learning, supernode assignment, aggregation, and feedback components with Euclidean counterparts, while retaining supernode compression and global structural collaboration. The three controls use the same encoder architecture and share the same pretrained checkpoint before grouping for each dataset and seed. They differ only in their supernode grouping strategies:
The three Euclidean variants reconstruct groups at the beginning of each outer iteration and use the within-group mean of unnormalized Euclidean node embeddings as the supernode representation. They replace hidden geometric statistics with observed coarse-graph degrees and use corresponding Euclidean server learning and feedback operations. Each variant reconstructs its coarse graph from the same original edge records using its own assignment matrix, preserving actual cross-client connectivity.
Results. Experiments cover Cora, CiteSeer, Amazon Photo, and Amazon Computers.
Final clustering uses K-means on original-node representations: Full uses unit-normalized node embeddings, while the Euclidean baselines use unnormalized Euclidean vectors. The table reports mean±sample standard deviation of ACC (%) across five training seeds.
Compared with the strongest Euclidean baselines on each dataset, FedSuCo improves ACC by 26.25, 22.51, 26.37, and 14.96 percentage points, respectively. The advantage is consistent across all five paired training seeds. FedSuCo also achieves higher NMI, ARI, and Macro-F1 than all three Euclidean baslines. Results indicate the effectiveness of its integrated geometric design.