- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3(+1)
Read review
Paper summary
The paper addresses Federated Class-Incremental Learning (FCIL), where at the same global round the same class can simultaneously be current, historical, or global-only across participating clients. The authors name this Asynchronous Class Exposure (ACE), and propose treating FCIL as co-evolution of a global model and a shared rehearsal state. Their PRO (Projected Rehearsal Orchestration) decomposes each round into READ–OPTIMIZE–WRITE: balanced pre-adapter rehearsal plus fresh WRITE under the aggregated global encoder to eliminate coordinate mismatch; PRO-MAX adds kernel-regression estimation of conditional class-mean displacement when no fresh WRITE is available. PRO-MAX achieves the highest mean Final Average Accuracy on six image / text / graph benchmarks (CIFAR-100, TinyImageNet, THUCNews-10, CLINC150, Cora, ogbn-arxiv). The theoretical appendix (App. B) gives six propositions and one theorem with explicitly stated scope; ablations isolate placement + refresh from feature-spread and replay fidelity.
Critical strengths
-
Conceptual reframing of FCIL around ACE and co-evolution. Naming ACE (current / historical / global-only) and treating FCIL as joint evolution of (\Theta_r^g, M_r) rather than "model with frozen memory" gives a clean lens on a fragmented literature. The three failure modes (“bypass adapter” / “coordinate mismatch” / “staleness”) map one-to-one onto READ–OPTIMIZE–WRITE, making the design choices feel necessary rather than ad-hoc.
-
Methodologically tight and modality-agnostic. PRO is closed-form on the server; PRO-MAX MOVE is a small, inspectable kernel-regression step that explicitly does not attempt covariance recovery; the per-class memory interface is reused unchanged across CIFAR-100 / TinyImageNet / THUCNews-10 / CLINC150 / Cora / ogbn-arxiv; PRO-MAX is the strongest reported method on every one of the six streams, and ablations (Fig. 3 and Tables 3–4) isolate placement + refresh from feature-spread and replay fidelity.
Critical weaknesses
-
Replay-object budget is not matched. Table 9 makes the asymmetry explicit (HR / FedCBDR / TARGET / MFCL get 100 replay objects vs. PRO / PRO-MAX at 20) and acknowledges it ("object-count configurations, not matched-byte, matched-information, or matched-compute regimes"), but does not run the controlled experiment that would be needed to fully separate the algorithmic contribution from the resource asymmetry — e.g. HR / FedCBDR / TARGET / MFCL reduced to 20 replay objects, or PRO / PRO-MAX expanded to 100 projected pseudo-features.
-
Scope and directness of the ACE measurement. The headline setting (40/50/60) conflates three interventions — task-support, label coverage and task-order perturbation — rather than directly realising ACE (two clients disagreeing about the role of the same globally exposed class in the same round). Appendix D is transparent ("severe heterogeneity in the retained tables denotes this reference setting, not a measured ACE value"), but the headline claim "transfer under ACE" is not directly tested. Theoretical results are per-round with no convergence / generalisation analysis of the federated training procedure (App. B.6).
Questions for authors
-
Could you re-run the heterogeneous CIFAR-100 comparison under matched replay budgets (e.g. HR / FedCBDR / TARGET / MFCL with 20 replay objects and PRO / PRO-MAX with 100 projected pseudo-features, or matched FLOP / matched bytes)? This would let the reader separate the proposed algorithmic choice from the asymmetry in Table 9.
-
Could you add a control that exposes an explicit ACE rate — e.g. per round, the fraction of globally exposed classes that two participating clients assign to different roles (current vs. historical vs. global-only) — and report FAA / AF / CTA as a function of that ACE rate? This would let the community verify the ACE-centric narrative more directly than the bundled 40 / 50 / 60 setting does.
-
Could you provide a short ablation on the size of the calibration set, the choice of K for KNN, and the bandwidth \tau_{c,y} (median heuristic vs. cross-validated scale) in PRO-MAX MOVE, so that the gap between PRO and PRO-MAX can be attributed cleanly to the bandwidth / weight scheme rather than to the extra forward passes?
7 comments
We are grateful for your detailed comments. We respond to each question below.
Q1. Matched replay budgets
A1. Thank you for suggesting this comparison. To address the budget difference, Table R11 compares 20 and 100 replay objects per historical class, participating client, and local epoch. The original settings use 100 for TARGET, MFCL, HR, and FedCBDR and 20 for PRO and PRO-MAX (paper Table 11). Each method retains its architecture and initialization. Loss weights for each source and optimizer updates are controlled separately.
Table R11. FAA at 20 and 100 replay objects (paper Table 3).
| Method | FAA, 20 objects | FAA, 100 objects |
|---|---|---|
| TARGET | 27.15 | 27.86 |
| MFCL | 28.71 | 29.42 |
| HR | 31.47 | 32.18 |
| FedCBDR | 38.25 | 38.96 |
| PRO | 43.28 | 43.99 |
| PRO-MAX | 46.12 | 46.83 |
PRO and PRO-MAX exceed FedCBDR by 5.03 and 7.87 FAA points at either count (Table R11). The ordering is unchanged, but these are mean comparisons. Results for individual seeds and paired uncertainty are unavailable for this control.
Beyond replay count, paper Table 4 compares methods using the same architecture and training policy. At 20 objects, this raises FedCBDR to 43.93 FAA. PRO is then 0.65 lower and PRO-MAX 2.19 higher. Section 4 distinguishes these margins from matching only object counts. Equal counts still allow differences in information content, storage, and FLOPs because images and feature vectors require different resources.
Q2. Realized ACE and performance
A2. Thank you for requesting explicit ACE rates. Eq. (21) measures role disagreement for a pair of participating clients and a globally exposed class. The 40/50/60 configuration describes the sampler settings. It is not itself an ACE measurement.
Using this definition, Table R12 reports mean ACE from our exposure simulation with fixed ownership and participation while changing order.
Table R12. Stream-average ACE from the exposure simulation (paper Table 45).
| Order perturbation | Stream-average ACE |
|---|---|
| 0% | 0.33815 |
| 30% | 0.25249 |
| 60% | 0.22996 |
| 90% | 0.22304 |
If more clients assign a class to the global-only role, disagreement can fall despite greater order perturbation. However, these ACE values do not come from the training sweep, so they cannot provide the requested relationship between ACE and FAA, AF, or CTA in the same runs.
For performance, the training sweep in paper Table 29 provides separate evidence. From 0% to 90% perturbation, FAA falls by 8.02, 2.92, and 2.66 points for FedCBDR, PRO, and PRO-MAX. AF rises from 30.96 to 46.92, 28.64 to 36.58, and 24.22 to 31.24, respectively. These results support lower sensitivity to ordering. Relating these performance results to ACE still requires role histories and metrics from the same runs, with labeled sample identities, ownership, and counts fixed. Order also changes recency, so this intervention cannot isolate ACE as a causal factor.
For the theoretical question, Proposition 1 separates class coverage and weighting from feature mismatch.
In this bound, uniform rehearsal over every exposed class removes the first term even when local roles differ. The remaining feature mismatch motivates WRITE and MOVE. Appendix I explains these operations at a fixed stage without establishing convergence or generalization of the full training process. ACE describes the exposure setting and is not itself the error term in this bound.
Q3. Calibration size, neighbors, and bandwidth
A3. Thank you for suggesting these controls. Table R13 varies K with 128 calibration samples. Table R14 varies calibration size with .
Table R13. Sensitivity to K with 128 calibration samples (paper Table 35).
| K | FAA | AF |
|---|---|---|
| 1 | 43.92 | 30.86 |
| 3 | 45.38 | 27.42 |
| 5 | 46.12 | 26.18 |
| 10 | 45.94 | 26.74 |
| 20 | 44.26 | 29.62 |
Table R14. Sensitivity to calibration size with (paper Table 37).
| Calibration samples | FAA | AF |
|---|---|---|
| 16 | 43.84 | 31.04 |
| 32 | 44.96 | 28.72 |
| 64 | 45.68 | 27.36 |
| 128 | 46.12 | 26.18 |
| 256 | 46.24 | 26.02 |
In the neighborhood sweep, intermediate values of K give the strongest means. Increasing calibration from 128 to 256 adds 0.12 FAA and reduces AF by 0.16 points. This supports the selected setting but does not establish statistical equivalence between nearby settings.
To examine the transport estimate itself, Table R15 tests the contribution of the estimated movement.
Table R15. Mean FAA and AF for transport controls (paper Table 15).
| Variant | FAA | AF |
|---|---|---|
| PRO | 43.28 | 31.54 |
| Zero transport | 43.32 | 31.50 |
| Shuffled class | 42.86 | 33.06 |
| Uniform weights | 44.90 | 28.66 |
| PRO-MAX | 46.12 | 26.18 |
PRO-MAX exceeds zero, shuffled, and uniform transport by 2.80, 3.26, and 1.22 FAA points. Zero transport stays close to PRO despite retaining the additional code path. These controls support the value of estimating movement for each class.
However, to isolate the effect of extra forward passes, a control must match forward calls, normalization updates, and random draws while suppressing both local and server movement. Because the current code description does not verify all these details, the control does not fully isolate this effect.
Finally, the comparison between median and cross-validated bandwidths is not reported. Uniform weighting also changes the estimator and may change aggregation support. Its 1.22-point gap therefore does not isolate bandwidth. A bandwidth comparison must keep the kernel family, neighbors, calibration inputs, and aggregation rule fixed while changing how the scale is selected. Appendix J.4 states that these controls support the tested transport setting without establishing that the median heuristic is optimal.
The statement of AI documentation
I have filled out the AI documentation. The review was independently assessed by me. An LLM was only used for language polishing; all technical evaluation and the final score are my own judgment. There is no mismatch between my human assessment and the AI-assisted drafting. I will actively join the discussion with authors and the AC during the discussion period.