- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
I understand FedConsult as a framework for sharing the strengths of personalized federated models through compact visual adapters. it identifies samples where personalization improves over a global predictor, groups their prediction-correction directions, and distills each group into an adapter. Each recipient then learns a response-aware router that combines adapter responses with its original prediction. the experiments report improvements in overall accuracy and accuracy on clients’ weakest classes.
Critical strengths
I find the shared feature interface a sensible way to transfer personalized knowledge. each recipient interprets an adapter’s correction through its own prediction pathway, addressing the compatibility problem of directly transferring another client’s classifier. each adapter contains only 512 parameters, which also keeps the additional communication small.
I also appreciate the experiments examining where the gains come from. The component ablations and comparisons with local-only, random, and averaged adapters provide useful evidence that learned external expertise contributes beyond additional local adaptation. The prediction-transition analysis further supports the intended benefit for weaker client–class pairs.
Critical weaknesses
Actually I have a concrete concern about the specialty decomposition on the binary medical tasks. For 2 classes, centering and normalizing the logit correction in Equation (3) leaves only two possible directions. however he paper uses four directional clusters per client on Retina and BreaKHis without explaining how duplicate centers or empty clusters are handled. This does not rule out useful adapters, but it leaves their construction unclear and weakens the interpretation that these results demonstrate four distinct correction specialties. I am also concerned about the independence of the medical evaluation. Appendix A.3 describes image-level partitioning followed by local train–test splitting, while BreaKHis contains multiple images from each of only 82 patients. the stated protocol does not establish patient-disjoint evaluation, so correlated images from the same patient could appear in training and testing. i cannot determine from the paper whether this occurred, but without clarification or results on grouped splits, the evidence for generalization to unseen patients is insufficient for a positive recommendation.
Questions for authors
How is four-way directional clustering implemented on the binary tasks? I would like to see the resulting cluster occupancies and comparisons with two adapters and random within-class partitions on Retina and BreaKHis to understand what the decomposition contributes.
Are all medical training and test sets disjoint at the patient or lesion level, including across clients? If this was not enforced, could you repeat the main comparisons with grouped splits and report variability across multiple runs? These results would materially affect my assessment.
4 comments
Concern 2: Medical Data Separation and Variability
Are all medical training and test sets disjoint at the patient or lesion level, including across clients? If this was not enforced, could you repeat the main comparisons with grouped splits and report variability across multiple runs? These results would materially affect my assessment.
Response:
We thank the reviewer for pointing this out. We have reviewed the data further, strengthened the separation of identified groups of related images across training/test sets and across clients in Skin14 and BreaKHis, and repeated the benchmark comparisons and three-seed experiments on the revised splits. The results support FedConsult's effectiveness under stricter separation, and the repeated runs also support its performance advantage.
Our original splits followed the official protocols of FedDRM, FedKWAZ, and dFLMoE. Following your suggestion, we reviewed the data further and adopted stricter preprocessing and grouped partitioning to ensure that each identified patient, lesion, or case group belongs to exactly one client and appears exclusively in either training or testing. We then repeated the experiments for FedConsult and the comparison methods under this protocol.
- Skin14: Our review identified pre-generated variants, conflicting labels, and records that could not be linked to a patient identity. After removing these records, we retained 23,367 images and applied grouped separation using the available patient or lesion identifiers.
- BreaKHis: We conservatively grouped images by their year/numeric case prefixes, keeping section and magnification variants potentially belonging to the same patient together. The resulting dataset contains 7,909 images.
Both revised datasets use five clients to maintain sufficient class-specific samples per client after grouped separation and avoid missing rare classes due to excessive fragmentation. We retain the Dirichlet heterogeneity setting of , allocate data at the group level, and maintain an approximately 70/30 train/test ratio, ensuring that every client has training and test samples from each class. Our additional review of Retina identified no new issues, so we retain FedDRM's official preprocessing and three-center split.
The benchmark results on the revised splits are reported below (%).
| Method | Skin14 Acc | Skin14 Weak | BreaKHis Acc | BreaKHis Weak |
|---|---|---|---|---|
| FedAvg | 62.81 | 9.18 | 80.12 | 43.62 |
| FedProx | 61.21 | 14.07 | 81.37 | 41.41 |
| FedSAM | 65.07 | 14.10 | 81.08 | 40.72 |
| FedALA | 68.65 | 7.14 | 85.18 | 31.40 |
| FedPAC | 68.22 | 0.00 | 85.60 | 35.35 |
| FedAS | 68.42 | 6.20 | 85.10 | 33.70 |
| DualFed | 67.38 | 7.95 | 86.26 | 38.60 |
| ConFree | 68.29 | 4.65 | 86.35 | 29.53 |
| cwFedAvg | 67.62 | 2.88 | 83.80 | 30.93 |
| Fed-MoE | 65.95 | 0.00 | 83.05 | 43.12 |
| PM-MoE | 67.23 | 7.95 | 87.18 | 44.89 |
| FedFew | 69.05 | 0.00 | 85.81 | 31.86 |
| FedDRM | 69.08 | 4.62 | 82.63 | 32.60 |
| FedConsult (Ours) | 69.62 | 12.86 | 88.11 | 52.51 |
FedConsult retains the highest accuracy (Acc) among the evaluated methods on both datasets under the revised splits, which enforce stricter data separation.
Following your suggestion, we also evaluated stability across three random seeds. We selected ConFree, FedFew, and FedDRM as three representative methods with strong performance on the medical datasets and repeated their experiments alongside FedConsult using the same grouped splits. Results are reported as mean ± standard deviation (%).
| Method | Skin14 Acc | Skin14 Weak | BreaKHis Acc | BreaKHis Weak |
|---|---|---|---|---|
| ConFree | 68.23 ± 0.28 | 3.63 ± 1.81 | 86.54 ± 0.28 | 29.76 ± 2.22 |
| FedFew | 68.22 ± 0.72 | 1.31 ± 1.53 | 86.02 ± 0.19 | 36.28 ± 4.11 |
| FedDRM | 68.39 ± 0.85 | 4.84 ± 1.32 | 84.02 ± 2.17 | 32.49 ± 6.86 |
| FedConsult (Ours) | 69.55 ± 0.18 | 13.11 ± 1.54 | 89.23 ± 0.97 | 54.40 ± 8.07 |
These three-seed results further support FedConsult's stability on the revised splits.
We have updated the data partitioning procedures and results in the revised manuscript.
Thank you very much for your comments. As the discussion period is drawing to a close, we would like to ask whether our responses have addressed your concerns. If you have any further questions, we would be happy to address them in the remaining time.
Thank you for the detailed rebuttal and additional experiments. The new results have addressed some of my main concerns. Therefore, I am raising my rating from 2 to 3.
Concern 1: Directional Clustering on Binary Tasks
Response:
We thank the reviewer for pointing this out. We set M=4 as an upper bound and handle insufficient samples or distinguishable directions by limiting the actual cluster count and training adapters only for nonempty groups. Centering and normalizing binary logit corrections yields at most two nonzero directions, ±(1,−1)/2, so four directional clusters are not enforced. We have added the effective cluster counts and comparisons with M=2, M=1, and random within-class partitions to explain the actual construction and evaluate the contribution of decomposition.
Specifically, after obtaining a nonempty specialty sample set using Eq. (2), we first limit the actual cluster count according to the available samples and distinguishable directions:
Ki=max1,min(M,Ni,Ui),
where Ni is the number of selected samples and Ui is the number of distinct centered and normalized direction vectors after rounding to six decimal places. If Ki=1, all samples are assigned directly to one group. Otherwise, we use k-means++ initialization and apply the utility-weighted K-means in Eq. (4).
After clustering, we remove unoccupied cluster labels and train adapters only for nonempty groups, without duplicating centers or adding groups to reach four. Thus, when samples or distinguishable directions are insufficient, fewer adapters are constructed rather than forcing the training of experts without sufficient sample support.
On Retina and BreaKHis with the revised grouped split, setting the upper bound to four or two produces the same groups. The effective cluster counts are reported below:
The final expert banks contain neither empty groups nor duplicate centers among occupied clusters. These binary-task results correspond to the two directional clusters actually formed, rather than four distinct correction directions.
Following your suggestion, we have added comparisons on Retina and BreaKHis between directional grouping with M=2, a single adapter distilled from all selected samples (M=1), and two adapters distilled from random within-class partitions. For the random control, we randomly divide each class's selected samples into two subsets, then pool subsets with the same index across classes. All other training settings are held constant.
Directional grouping outperforms pooled distillation with M=1 on both datasets, supporting the value of distilling different correction patterns separately. It also outperforms random within-class partitioning at the same adapter count, showing that organizing distillation samples by correction direction provides practical benefits. These results support the value of both decomposition and the grouping strategy, beyond simply increasing the number of adapters.
We have clarified the clustering procedure in the revised manuscript.