- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces a federated generative recommendation model using hierarchical Semantic IDs, namely FedGReS. Specifically, it builds shared relation graphs from SID transition and co-occurrence statistics collected on local clients. Two graph-attention modules then refine the SID representations for a TIGER-based recommender. Experiments are conducted on three Amazon Reviews 2023 datasets, with comparisons against federated recommendation baselines.
Critical strengths
- The idea of sharing coarse Semantic ID relations is reasonable.
- The experimental evaluation is fairly comprehensive.
Critical weaknesses
- Although different client partitions are evaluated, it is unclear how much of the improvement comes from addressing history fragmentation rather than general relation sharing.
- The related-work section explicitly discusses FedCGR (Liu et al., 2026), which also studies SID-based federated generative recommendation, but FedCGR is not included in Table 1.
- Since secure aggregation is optional, the server may access client-level relation statistics. It is unclear whether these shared statistics could reveal sensitive information. Thus, the privacy protection may need further clarification.
- The evaluation under different client heterogeneity settings is limited to the Video dataset.
Questions for authors
- Could the authors provide more direct evidence that FedGReS helps address fragmented shared-user histories?
- Would it be possible to add FedCGR (Liu et al., 2026) as one of the baseline methods?
- Could the authors clarify the privacy implications of sharing client-level relation statistics?
- Could the authors extend the client heterogeneity experiments to Software and Baby datasets?
4 comments
Response to Reviewer Ftxy [2/2]
- Weakness 3 and Question 3. Privacy implications
Response to Weakness 3 and Question 3. Thank you for requesting clarification. We have revised the “Privacy and communication scope” paragraph in Section 4.2 and added Appendix B. FedGReS aims to protect user identities, specific user–item associations, and records identifying which item pairs occur in a local sequence. Coarse first-level SID relations are intentionally shared as collaborative knowledge and fall outside the information we aim to conceal.
Even when the server receives raw client-level counts, the matrices record first-level SID transitions and co-occurrences aggregated across users, without identifying the contributing item pairs, users, or sequences. Replacing items with locally available alternatives sharing the same first-level codewords, while preserving sequence positions and boundaries, leaves both count matrices unchanged. Reassigning complete histories among users within the same client likewise preserves the counts. A specific user–item or item-pair fact is therefore not uniquely determined when such alternatives remain compatible with the observer's knowledge and differ on that fact. This ambiguity is inherent to the count representation and does not depend on secure aggregation.
Without secure aggregation, the server can still observe each client's coarse relation patterns and exact counts. We explicitly identify this disclosure as a limitation in Appendix B. For applications requiring confidentiality of these patterns, future work will investigate controlled count perturbation and its privacy–utility trade-off.
- Weakness 4 and Question 4. Heterogeneity experiments on Software and Baby datasets
Response to Weakness 4 and Question 4. Thank you for this suggestion. We agree that extending the heterogeneity evaluation beyond Video strengthens the empirical assessment. We conducted additional experiments on Software and Baby, prioritizing comparison with FedProx, a strong baseline in the Video study that explicitly addresses heterogeneous federated optimization. Experiments with the remaining baselines are ongoing, and we will supplement the revised manuscript with the complete comparisons once they finish.
We follow the same data-partitioning and training protocols as the Video study, using the hyperparameter-selection procedure described in Appendix C.4.
| Dataset | Method | R@5 | N@5 | R@10 | N@10 | |
|---|---|---|---|---|---|---|
| Software | FedProx | 0.0739 | 0.0477 | 0.1121 | 0.0600 | |
| FedGReS | 0.0734 | 0.0474 | 0.1118 | 0.0599 | ||
| FedProx | 0.0748 | 0.0491 | 0.1143 | 0.0618 | ||
| FedGReS | 0.0778 | 0.0506 | 0.1184 | 0.0637 | ||
| FedProx | 0.0716 | 0.0462 | 0.1113 | 0.0590 | ||
| FedGReS | 0.0769 | 0.0509 | 0.1148 | 0.0631 | ||
| FedProx | 0.0707 | 0.0450 | 0.1109 | 0.0580 | ||
| FedGReS | 0.0745 | 0.0475 | 0.1152 | 0.0606 | ||
| FedProx | 0.0666 | 0.0432 | 0.1020 | 0.0547 | ||
| FedGReS | 0.0703 | 0.0461 | 0.1054 | 0.0575 | ||
| FedProx | 0.0563 | 0.0365 | 0.0899 | 0.0473 | ||
| FedGReS | 0.0594 | 0.0384 | 0.0913 | 0.0488 | ||
| Baby | FedProx | 0.0163 | 0.0107 | 0.0260 | 0.0138 | |
| FedGReS | 0.0181 | 0.0118 | 0.0266 | 0.0145 | ||
| FedProx | 0.0178 | 0.0114 | 0.0277 | 0.0146 | ||
| FedGReS | 0.0179 | 0.0115 | 0.0285 | 0.0149 | ||
| FedProx | 0.0187 | 0.0117 | 0.0273 | 0.0145 | ||
| FedGReS | 0.0187 | 0.0117 | 0.0278 | 0.0147 | ||
| FedProx | 0.0164 | 0.0108 | 0.0244 | 0.0135 | ||
| FedGReS | 0.0165 | 0.0104 | 0.0246 | 0.0131 | ||
| FedProx | 0.0147 | 0.0088 | 0.0222 | 0.0112 | ||
| FedGReS | 0.0152 | 0.0094 | 0.0220 | 0.0117 | ||
| FedProx | 0.0152 | 0.0097 | 0.0212 | 0.0117 | ||
| FedGReS | 0.0161 | 0.0100 | 0.0215 | 0.0117 |
Across the 48 dataset–configuration–metric comparisons, FedGReS achieves higher scores in 38, matches FedProx in 3, and obtains lower scores in 7. The 7 deficits range from 0.0001 to 0.0005 in absolute score. These results show that FedGReS remains competitive beyond Video and support its effectiveness across the tested datasets, client distributions, and federation sizes.
I appreciate the authors' substantial efforts in revising the manuscript. The new subgroup analysis provides more direct evidence of the benefits of FedGReS for fragmented shared-user histories, and the inclusion of FedCGR makes the baseline comparison more complete. The revised privacy discussion also clarifies the scope and limitations of sharing coarse-grained relation statistics. Additional heterogeneity results on Software and Baby are also helpful.
Overall, I appreciate the authors' efforts and the improvements made in the revised manuscript. I have therefore decided to increase my rating from 2 to 3.
Response to Reviewer Ftxy
Dear Reviewer Ftxy,
We sincerely thank you for your valuable feedback and for updating your rating. We are glad that our revisions addressed your concerns.
Response to Reviewer Ftxy [1/2]
Dear Reviewer Ftxy,
We sincerely thank the reviewer for your time and insightful feedback. We are grateful for the positive assessment of our work and the constructive comments, which help us significantly improve our paper. All comments have been carefully addressed, and the corresponding revisions have been updated in the revised paper with major changes highlighted in purple for clarity. We hope our revisions address all the concerns and bring the paper up to acceptance.
Below, we provide point-by-point responses to each comment, along with additional explanations and experimental results where necessary.
Response to Weakness 1 and Question 1. Thank you for raising this point. We agree that the benefit to fragmented shared-user histories should be examined more directly. We have added a targeted analysis in Section 5.3 and its evaluation protocol in Appendix D.2 of the revised manuscript.
We reused the original three-client partitions and model checkpoints from the main comparison in Section 5.2 on Video, Software, and Baby. The analysis focuses on shared-user predictions for which local relational evidence is weak and additional evidence is available from other clients. For a test record e, let ae and be denote the first-level SIDs of the last input-history item and the target item, respectively. For each graph type g∈{tr,co}, Lg(e) is the local training count of this relation, Rg(e) is its summed training count on the other clients, and Aaebeg is its weight in the deployed pooled graph. We define
B = \left\\{e \in \mathcal{D}_{\mathrm{shared}} : \exists g \in \\{\mathrm{tr},\mathrm{co}\\},\\; L_g(e) \leq 20 \land R_g(e) > L_g(e) \land A^g_{a_e b_e} > 0\right\\}.
where Dshared contains the client-local test records of shared users. All denotes the full test set, including B.
Test records (All / B): Video 16,625 / 4,497; Software 32,514 / 5,722; Baby 18,464 / 3,761.
Across all three datasets and both cutoffs, FedGReS achieves larger relative gains on B than on All. The absolute Recall gains are also larger on B in every comparison. These results support FedGReS's ability to mitigate the effects of fragmented shared-user histories by supplementing weak local relational evidence with transition and co-occurrence patterns from other clients.
Response to Weakness 2 and Question 2. Thank you for this suggestion. We have added FedCGR as one of the baseline methods. FedCGR's original backbone performed better during tuning, so we retained it. We follow the original FedCGR settings for the generator and SASRec architectures, CF adapter, private experts, expert dimensions and routing, auxiliary loss weights, contrastive temperature, prototype EMA, and generator batch size.
Tuned hyperparameters:
Main comparison. The table below compares FedCGR and FedGReS on all three datasets.
FedCGR is competitive with the existing baselines. Nevertheless, FedGReS outperforms FedCGR on all four metrics across all three datasets, with relative Recall@5 improvements of 6.93%, 3.19%, and 7.60% on Video, Software, and Baby, respectively.
Data heterogeneity and federation size. We also evaluated FedCGR on Video under varying data heterogeneity and federation sizes. We have updated Sections 5.2 and 5.6 of the revised manuscript to include these additional comparisons. FedGReS consistently outperforms FedCGR on all four metrics across the tested settings.