- The novelty claim regarding exemplar complementarity should be positioned more carefully. Recent studies have already considered diversity or marginal contribution in replay selection. Krutsylo (2024) explicitly studies inter-batch diversity and removes redundant neighboring samples; Tong et al. (2025) evaluate samples by the performance gain obtained when they are added to a coreset; and Yanowsky and Weinshall (2026) use complementary supervised and self-supervised embeddings for replay selection. Therefore, RECALL’s novelty appears to lie in its specific combination rather than in introducing complementarity itself. The authors should clarify this distinction and compare with recent diversity-aware selectors under the same memory budget.
[1] A. Krutsylo, “The Inter-batch Diversity of Samples in Experience Replay for Continual Learning,” AAAI, 2024.
[2] R. Tong et al., “Coreset Selection via Reducible Loss in Continual Learning,” ICLR, 2025.
[3] D. Yanowsky and D. Weinshall, “Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers,” arXiv:2604.08336, 2026.
-
The experimental protocol does not specify how the test data are partitioned or whether evaluation is centralized or client-specific. Moreover, the authors should justify the use of 1/\sqrt{n_{i,c}}, which gives each client-class approximately equal total weight regardless of its sample size. It is unclear whether this assumption is appropriate under heterogeneous data distributions, particularly when some local classes contain very few samples. An ablation with alternative weighting strategies would strengthen the justification.
-
RECALL combines approximately class-balanced client-side quotas with residual-based selection, but their interaction is not examined. Under long-tailed data, this allocation may assign memory without considering class complexity, while residual maximization may also favor outliers.
-
The paper lacks an overall framework diagram. Please add one to clearly illustrate the roles and relationships of the three proposed modules.
-
The experiments only consider Dirichlet parameters beta=0.5 and 1.0, representing relatively mild-to-moderate heterogeneity. Please include more severe non-IID settings, e.g., beta=0.1 and 0.01, to better evaluate the robustness of RECALL under highly heterogeneous client distributions.
-
Most individual components of RECALL, such as diversity-aware replay, coreset-based exemplar selection, class-balanced memory, and feature distillation, have been explored previously. Its novelty therefore appears to lie mainly in their integration. The authors should clarify the specific technical advances beyond a straightforward combination of existing techniques.
-
All experiments use only ResNet-18. Please evaluate RECALL with at least one additional backbone to demonstrate its architectural generality.
-
Preserving sample diversity does not necessarily imply a direct correlation with performance improvements; the authors need to specify the conditions under which this paper applies.
-
The article states that previous approaches resulted in a large number of duplicate or redundant samples, but there are no experiments to support this claim.