- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies task-free streaming federated continual learning, where clients receive short-lived data chunks with arbitrary class overlap and need to perform inference on all previously seen classes. The authors propose FedKACE, which combines a gradient-responsive replay scheme to balance new and old knowledge, a buffer maintenance strategy to retain important samples, and an adaptive mechanism to switch between local and global models for inference. Experiments on CIFAR100 and ImageNet100 under different class overlap settings show that FedKACE outperforms the evaluated baselines in average accuracy. The paper also provides theoretical analyses to support the proposed framework.
Critical strengths
-
The paper addresses a meaningful and challenging problem in federated continual learning by considering streaming data with arbitrary class overlap and no explicit task boundaries. This setting relaxes several common assumptions in existing FCL methods and is relevant to practical scenarios where data access and storage are limited. The problem is also clearly motivated and formulated.
-
The proposed framework combines three components to address knowledge retention, buffer management, and inference model selection in a coherent way. The experiments cover two datasets and several class overlap settings, with FedKACE consistently outperforming the evaluated baselines. The paper also includes ablation studies to examine the contributions of different components, providing useful empirical evidence for the proposed approach.
Critical weaknesses
-
Insufficient justification for the adaptive inference model switching criterion. In Section 4.3, the authors decide when to switch from the local model to the global model based on the change in the gap between the global model's accuracy and prediction confidence. However, a decreasing gap does not necessarily mean that the global model is improving, or that it has become better than the local model. For example, the gap could decrease even when the global model's accuracy drops. Moreover, the proposed criterion does not directly compare the two models, and the switch is irreversible even as new data continue to arrive. This raises concerns about whether the proposed criterion can reliably identify the right time to switch.
-
Limited justification for the gradient-responsive replay weighting strategy. In Section 4.1, the authors use the ratio of squared gradient norms between buffered and new samples to balance knowledge retention and acquisition. However, gradient magnitude alone may not reliably reflect knowledge forgetting or conflicts between old and new knowledge. For example, large gradients can also result from difficult samples or distribution shifts, while gradient directions are important for identifying conflicts between updates. In addition, the paper does not clearly explain why the squared gradient norm ratio is preferred over other gradient-based weighting strategies.
-
Limited baseline comparisons for the proposed task-free streaming setting. The experiments mainly compare FedKACE with traditional federated continual learning methods, many of which rely on explicit task boundaries or task identifiers. The authors adapt these methods by using FL rounds as task identifiers, but it is unclear whether this provides a sufficiently fair comparison, given the different assumptions of these methods. Although task-free online continual learning methods are discussed in the related work, their federated adaptations are not evaluated. As a result, the current comparisons may not fully demonstrate the advantages of FedKACE in the proposed task-free streaming setting.
Questions for authors
-
Could the authors further explain why a decreasing gap between accuracy and prediction confidence indicates that the global model has become better than the local model? It would be helpful to show how this gap relates to the actual performance difference between the two models over FL rounds, and compare the proposed criterion with a simple performance-based switching strategy
-
Could the authors clarify the motivation for using the squared gradient norm ratio, and how it relates to knowledge forgetting or conflicts? It would also be helpful to compare this choice with alternative strategies, such as the regular gradient norm ratio or methods that consider gradient directions, to better demonstrate the benefit of the proposed design.
-
Could the authors clarify how the task-dependent baselines were adapted to the proposed setting and whether these adaptations ensure fair comparisons? It would be helpful to include at least one task-free online continual learning method adapted to federated learning, under the same memory and training budgets, to further validate the effectiveness of FedKACE.
3 comments
For Question 2,We sincerely thank the reviewer for the careful observation and fully understand your concerns about whether gradient magnitude alone can reliably reflect knowledge forgetting or conflicts between old and new knowledge, as well as your questions about why the squared gradient norm ratio is preferred over other gradient-based strategies. We provide detailed clarifications and explanations for these critical issues below.
First, we would like to clarify that the weight is not a direct measure of "knowledge forgetting" or "gradient direction conflicts," but rather a proxy for the relative update pressure of the replay constraint versus the new data constraint. The ratio of squared gradient norms essentially corresponds to the gradient energy ratio, which is more sensitive to the relative changes in replay and task constraints. When the replay gradient is relatively larger than the task gradient, it indicates that the loss sensitivity of the model on old samples is relatively stronger; thus, increasing the replay weight strengthens the retention constraint for old knowledge. Conversely, decreasing the weight frees up parameter capacity for new knowledge acquisition. Moreover, this relative ratio inherently resists noise: global perturbations (e.g., distribution shifts) affect both losses and cancel out in the ratio, ensuring the weight only responds to single-sided imbalances for dynamic equilibrium.
Second, as you rightly pointed out, large gradients in a short time window can indeed result from the sampling of difficult samples or local distribution shifts. To mitigate this, instead of using single-batch instantaneous gradients, we compute the next epoch's replay weight via epoch-level running averages of both losses. This smoothing mechanism effectively filters out gradient spikes, ensuring a robust evolution that accurately reflects the macroscopic relative learning states of old and new knowledge.
Regarding the alternative strategies considering gradient directions you suggested, while effective in traditional CL, they face semantic and computational failures under our task-free, arbitrary-overlap streaming setting. Semantically, without task boundaries, old and new samples of the same class often yield synergistic rather than conflicting gradients, rendering directional conflict signals invalid. Computationally, full-model gradient projection requires storing all parameter gradients, which is prohibitive for edge clients. Our ablation (AS5) confirms this increases FLOPs by 2,780× to 35,600×. Thus, the output-layer gradient proxy remains the only feasible compromise balancing theoretical rigor and practical scalability.
Finally, regarding why the "squared" gradient norm is preferred over the "regular" gradient norm, this is not an arbitrary heuristic design but a mathematical necessity dictated by strict optimization theory. The regular L2 norm is non-differentiable (non-smooth) when the gradient approaches zero, which violates the fundamental assumptions in optimization theory. Conversely, the squared norm's smoothness ensures the quotient mapping is Lipschitz continuous near the equilibrium, a prerequisite for the Banach fixed-point theorem. Crucially, only the squared norm, combined with active parameter masking, strictly derives the "gradient energy balance" (yielding from ). This proves convergence to a perfectly balanced equilibrium, which non-squared norms cannot guarantee.
For Question 3,We sincerely thank the reviewer for the insightful comments. Regarding your concerns about the baseline comparisons and the fairness of the adaptations, we provide detailed clarifications and supplementary explanations below.
First, regarding the adaptation of Task-dependent FCL Baselines, we uniformly provided them with the FL round index as the explicit task identifier. The fairness of this adaptation is validated across settings. Specifically, under the setting, adjacent FL rounds have strictly disjoint class sets, which perfectly aligns with the "mutually exclusive class sets across tasks" assumption inherent to traditional FCL methods, making this comparison absolutely fair. Conversely, under , the class window remains fixed for 5 consecutive rounds, simulating the "static class sets" assumption in OCL. For partial overlaps (), arbitrary class overlap breaks traditional FCL assumptions. As shown in Table 1, traditional methods suffer significant performance degradation here, precisely demonstrating that their reliance on explicit task boundaries is an inherent limitation in streaming scenarios. Highlighting this gap is necessary, as overcoming this exact limitation is the core motivation for proposing FedKACE.
Second, we sincerely appreciate this constructive suggestion for including at least one task-free online continual learning method adapted to federated learning, we have supplemented a federated adaptation of a task-free OCL method DEMD[1], namely F-DEMD, as a new baseline to further validate the effectiveness of FedKACE.
[1] F. Ye and A. G. Bors, Online Task-Free Continual Learning via Dynamic Expansional Memory Distribution. CVPR2025
We thank the reviewer for patiently reading through this entire response, and we kindly invite the reviewer to examine the newly uploaded revised manuscript.
We sincerely thank the reviewer for reading our manuscript and providing valuable comments. Below, we present our point-by-point responses to the comments.
For Question 1,We thank the reviewer for the careful observation and constructive comments. We would like to clarify that the original intention of this switching criterion is not to directly compare the absolute performance of the two models in each round. Instead, it is designed to detect whether the global model has crossed the underfitting stage and achieved a good "prediction calibration" state on the client's local buffer, thereby determining its "usability" for the client for inference.
Regarding the concern that "the gap could decrease when accuracy drops," we highlight the truncation property of GAP=max(0,ACC−PROB). When a model overfits the local buffer, its accuracy (ACC) may stagnate or drop, but prediction confidence (PROB) surges abnormally. Consequently, PROB>ACC forces GAP to truncate directly to 0, rather than "slowly decreasing." Instead, ΔGAP<0 captures the global model's monotonic transition from "underfitting" (ACC>PROB) to "well-calibrated" (PROB steadily approaching ACC) in early FL rounds, indicating it has fully adapted to the local distribution.
Regarding the rationality of the "unidirectional irreversible switching" and the robustness of "decreasing for two consecutive rounds,", it stems from Streaming FCL constraints. With tiny buffers, local models inevitably suffer catastrophic forgetting from incoming classes, while global models monotonically enhance generalization via aggregation. Thus, once well-calibrated, unidirectional switching optimally counters local degradation. Meanwhile, requiring "ΔGAP<0 for two consecutive rounds" smoothly filters outliers, preventing misjudgments from single-round fluctuations and ensuring robust decisions. We have confirmed this through ablation studies (AS1 - AS3).
Finally, regarding the "simple performance-based switching strategy" suggested by the reviewer, we need to point out its fatal flaws under the current setting. In the Streaming FCL setting, clients do not have an independent validation set, and all buffer data are involved in the training of the local model. Therefore, the ACC measured by the local model on the buffer suffers from severe systematic bias (optimistic estimation/overfitting). Directly comparing this biased ACC with the global model would almost always result in the local model "winning," which would cause the switching logic to completely fail and make it impossible to determine when the global model is truly usable.