- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes FedVGA for federated learning under statistical heterogeneity. The method alternates between representation learning with a fixed shared classifier and classifier adaptation with a fixed, globally aggregated feature extractor. The classifier directions define a spherical Voronoi geometry, and local directions are aggregated using class counts and a directional-coherence score. The paper analyzes classifier-induced gradient deviation and geometry-error propagation. Experiments on CIFAR-10/100, Office-Caltech-10, and a ten-class DomainNet subset compare FedVGA with existing methods and examine its components, training dynamics, and computational cost.
Critical strengths
- A coherent training design supported by a targeted synchronization ablation.
The most compelling contribution is the placement of global feature aggregation before local classifier adaptation. This ensures that the classifier directions being consolidated are fitted under a common feature mapping, while client-specific classifier changes cannot directly influence representation updates within the same cycle. Appendix B appropriately distinguishes this design from existing shared-head methods such as FedNH and FedETF.
The deferred-aggregation ablation in Appendix G is particularly informative because it preserves the two local stages while removing the intermediate synchronization. Its accuracy drops from 37.93 to 28.39 on CIFAR-100 and from 66.02 to 60.45 on the DomainNet subset. This provides meaningful empirical support for the defining design choice, beyond the geometric interpretation of a normalized classifier.
- Consistent empirical gains with useful controls for the additional interaction stage.
Tables 1 and 3 show improvements over relevant competitors, including FedNH and FedETF, across both label and feature heterogeneity. Importantly, Appendix H compares 100 complete FedVGA cycles against 200 baseline rounds, matching the number of client-server interaction stages. FedVGA retains an advantage on all four datasets in these comparisons; for example, its DomainNet accuracy is 66.52 versus 62.22 for FedETF.
The reported computational measurements include both stages and the additional aggregation computations. Together with the fixed-geometry, joint-optimization, and deferred-aggregation ablations, these controls make the empirical case more convincing than a comparison based only on the nominal round count.
Critical weaknesses
- The experimental uncertainty and model-selection protocols are insufficiently specified.
Tables 1 and 3 report accuracy values with uncertainty terms, but the manuscript does not clearly state the number of independent runs, what the uncertainty terms represent, or which sources of randomness are varied. The component ablations in Tables 2 and 5 provide no uncertainty estimates.
Appendix D gives the main FedVGA configuration, but the exact baseline local-training settings and method-specific hyperparameters are not listed; referring to the recommendations in the original papers does not fully specify the implemented comparisons. The procedure for selecting the dataset-dependent geometry-confidence coefficient and the checkpoint-selection rule are also unclear.
These omissions do not negate the consistent larger gains, but they limit reproducibility and make the smaller component-level improvements difficult to assess. The paper states that implementation code is supplied, which is helpful, but the principal experimental protocol should also be explicit in the manuscript.
- The reliability interpretation of geometry-confidence weighting has weaker support than the Align-and-Adapt mechanism.
Proposition 1 establishes that the proposed score measures within-class directional coherence. It does not establish that a more coherent class representation produces a more accurate local classifier direction: a concentrated local distribution can still support a systematically biased direction. Theorem 4 is an error-propagation inequality applicable to arbitrary convex aggregation weights. The advantage specific to GCA appears in Proposition 3 only under a non-positive association between coherence and local site error.
The authors appropriately acknowledge this conditional interpretation, so I do not view it as an incorrect theoretical claim. However, the experiments provide limited direct evidence for the intended reliability relationship. The GCA ablation improves accuracy by 1.09 points on CIFAR-100, 2.01 points on DomainNet, and only 0.15 points on Office-Caltech-10, without uncertainty estimates or a sensitivity study.
Consequently, the evidence is stronger for the synchronized alternating training procedure than for the particular confidence-weighting rule. This limits the explanatory strength of the latter contribution, although it does not undermine the usefulness of the overall method.
Questions for authors
-
How many independent runs underlie Tables 1 and 3, and what exactly do the reported uncertainty terms represent? Which sources of randomness are varied, and are methods compared using matched partitions and seeds? Please also clarify the variability of the component ablations, particularly the small GCA improvement on Office-Caltech-10.
-
Please specify the baseline local-epoch counts, learning-rate schedules, and method-specific hyperparameters used in the comparisons. How were the geometry-confidence coefficient and evaluation checkpoint selected, and was a separate validation set used? Are the FedVGA results in Appendix H additional runs under the same training protocol as the main tables?
-
What empirical evidence supports the interpretation that higher directional coherence identifies more reliable local classifier directions in the evaluated settings? Can the authors assess this relationship using a clearly defined reference or held-out measure, and clarify how stable the GCA gains are across seeds and choices of the confidence coefficient?
These questions concern the reproducibility and interpretation of the existing contribution. Their answers would materially affect my confidence in the empirical conclusions and in the role attributed to GCA.
2 comments
Response to rebuttal
Thank you for your response; it has addressed most of my questions, and I will maintain my assessment.
Response to Question 1.
Thank you for requesting these clarifications. Tables 1 and 3 report mean accuracy ± standard deviation over three independent runs. The same set of random seeds is used across methods.
We acknowledge that the GCA gain of 0.15 percentage points on Office-Caltech-10 is small. As discussed in the paper, GCA is an optional module for geometry consolidation, and its benefit is not guaranteed across all settings. Our core contribution is the geometry-based Align-and-Adapt mechanism; its distinctions from related methods are detailed in Sec. 3.2 and Appendix B.1.
Component ablations (Table 2; accuracy %):
Response to Question 2 .
All baselines use the same number of local epochs. The original-paper learning rates, schedules, and method-specific parameters are summarized below.
We selected the GCA coefficient through a sensitivity analysis, setting λ=0.4 for CIFAR-10/100 and λ=0.8 for Office-Caltech-10/DomainNet.
We report the checkpoint with the highest test Top-1 accuracy observed during training. No separate validation set was used. The FedVGA results in Appendix H come from additional runs under the same training protocol. That comparison uses 100 FedVGA cycles versus 200 baseline rounds. We should have made this provenance explicit in the manuscript.
Response to Question 3 .
We acknowledge that we do not have a clear, direct empirical measure of geometric reliability. The term was intended as an explanatory interpretation, and the lack of direct measurement is a limitation of our work. Thank you for pointing this out.
Many mechanisms in contemporary empirical research also lack complete theoretical guarantees or a direct measure of their intended properties. Their benefits are often assessed through ablation studies, as we do here.
As explicitly discussed in the paper, GCA is neither guaranteed to outperform other aggregation rules in every setting nor an indispensable component of our core Align-and-Adapt mechanism. We acknowledge that its gains are small in some evaluated settings. We nevertheless included it because we believe it may offer greater advantages under more extreme experimental conditions or datasets, which is one direction for our future work.
GCA is therefore an optional additional module motivated by our analysis. Given this role, we respectfully ask that its contribution to the overall framework be reassessed in this context.
Thank you again for your constructive feedback. We hope our response addresses your concerns.