- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3(+1)
Read review
Paper summary
MemEvo-FCGL addresses federated class-incremental node classification through shared structural keys, bounded local key–value memory, and historical-memory retrieval. Client memory states guide server aggregation and knowledge transfer. The method reports the highest final average accuracy on five of six datasets against the protocol-matched baseline subset.
Critical strengths
Connects local knowledge retention and server coordination through a common representation.
Shows substantial gains on several datasets, particularly Coauthor CS, with five-run results and paired-seed comparisons.
Includes component ablations and task-wise accuracy/forgetting analyses.
Clearly discloses transductive access, unmatched comparisons, and the absence of formal privacy guarantees.
Critical weaknesses
MOTION, a directly relevant FCGL baseline, is not uniformly protocol-matched. Cora and CiteSeer also have task or training-budget mismatches. These disclosures are helpful, but controlled comparisons with the closest competitors remain necessary.
States summarize assignments of graph-conditioned embeddings, which reflect both features and topology. The experiments do not establish whether they capture structural compatibility beyond feature or class distributions, or whether state similarity predicts update compatibility.
Coordination combines aggregation and teacher selection, while memory evolution combines allocation, merging, and compression. Removing entire modules cannot identify which mechanism produces the gains. Comparisons against simpler fixed-memory alternatives are missing.
All experiments use three clients with full participation and short task streams. Robustness to more clients, partial participation, different task orders, and stronger client heterogeneity is unclear.
A fixed slot count does not establish storage or runtime efficiency. The paper lacks measured memory bytes, communication costs, and runtime comparisons, including server reference-graph reconstruction.
Questions for authors
Match MOTION and POWER under identical task splits, training budgets, and comparable memory budgets.
Compare structural-state coordination against label histograms and simple embedding summaries; measure its relationship with gradient conflict or transfer benefit.
Separately ablate state-aware aggregation, teacher weighting, slot merging, and capacity-triggered compression.
Evaluate memory-capacity sensitivity, longer streams, more clients, and partial participation.
Explain how historical keys and values remain compatible with the evolving encoder, and report sensitivity to representation drift.
9 comments
2. Structural states as an aggregation signal
The structural state compares clients by the distribution of their node embeddings over aligned keys. In Eq. (2), the base GNN embedding of node is softly assigned to the structural keys at client :
u_{k,i,p}=\left(1+\\|\mathbf{h}_{k,i}-\mathbf{k}_{k,p}\\|_2^2/\tau_s\right)^{-(\tau_s+1)/2}, \qquad q_{k,i,p}=\frac{u_{k,i,p}}{\sum_{p'=1}^{P}u_{k,i,p'}}. \tag{2}
Equation (4) averages these assignments over the task-visible nodes :
\mathbf{s}_k^{t,r}=\frac{1}{|\mathcal{V}_k^t|}\sum_{i\in\mathcal{V}_k^t}\mathbf{q}_{k,i}\in\Delta^{P-1}. \tag{4}
The server broadcasts the key bank so the same coordinates can be compared across clients. Equations (2) and (4) explain what this state can capture beyond the two controls. A change in neighbors can change the messages entering and hence the state, even with node features and class frequencies fixed. A label histogram stays the same under that change. The assignments also depend on the full embedding vector, so two clients with the same per-dimension means and standard deviations can occupy different keys if their embedding dimensions co-vary differently. The state depends jointly on features and connectivity through the GNN.
For aggregation, Eq. (5) combines the sample-count prior , where , with agreement for clients ( for a single client):
\omega_k=(1-\lambda_a)\pi_k+\lambda_a\frac{a_k}{\sum_\ell a_\ell}, \qquad (\boldsymbol{\theta}_g,\mathbf{K}_g)=\sum_k\omega_k(\boldsymbol{\theta}_k,\mathbf{K}_k). \tag{5}
The normalized agreement term gives more weight to clients whose current states are closer to those of their peers, while the sample-count term preserves the contribution of data volume. The same state also informs teacher weighting in Eq. (6). For a reference node , the overlap between its assignment and client ’s state gives a node-specific weight:
b_{k,u}=\sum_p\sqrt{\widetilde{q}_{k,u,p}s_{k,p}}, \qquad \alpha_{k,u}=\frac{b_{k,u}}{\sum_\ell b_{\ell,u}}. \tag{6}
Equation (5) measures agreement in occupied modes across clients, and Eq. (6) matches reference nodes to those modes. Both use representation similarity as a proxy for where an update or teacher may be useful. Applying the source update to the global model gives the following first-order approximation to the validation gain:
where is the target validation loss. State similarity measures overlap in occupied modes, so whether it tracks this gain is an empirical question.
Controlled aggregation experiments. We evaluated the three signals over the original full task streams on Cora and Chameleon, using three clients and five paired seeds per dataset. We compared structural states with normalized histograms of current-task training labels and summaries formed from the per-dimension means and standard deviations of current-task node embeddings. We changed the similarity input to Eq. (5) and used the same mixing coefficient, , across the three variants.
The table reports the full-stream summary for final average accuracy (AP) and forgetting (FM), shown as mean ± standard deviation.
| Dataset | Aggregation signal | AP (%) ↑ | FM (pp) ↓ |
|---|---|---|---|
| Cora | Label histogram | 70.09 ± 5.25 | 14.06 ± 5.91 |
| Cora | Embedding mean and standard deviation | 60.71 ± 4.19 | 10.95 ± 1.46 |
| Cora | MemEvo-FCGL structural state | 79.65 ± 2.95 | 7.09 ± 2.20 |
| Chameleon | Label histogram | 45.98 ± 1.39 | 13.82 ± 0.90 |
| Chameleon | Embedding mean and standard deviation | 48.79 ± 2.51 | 11.74 ± 1.62 |
| Chameleon | MemEvo-FCGL structural state | 57.63 ± 0.96 | 6.42 ± 0.77 |
Relationship to transfer benefit. At rounds 1, 8, and 15 of each task, we computed all three similarities on the same client updates from the structural-state runs. For each directed source–target pair, we measured transfer gain as the reduction in the target client’s validation cross-entropy when using the source client’s locally updated model in place of the pre-aggregation global model. We computed Spearman correlations within each sampled round and averaged them over rounds and then over the five seeds.
| Dataset | Target task | Label histogram ρ | Embedding summary ρ | Structural state ρ |
|---|---|---|---|---|
| Cora | Current | 0.393 | 0.467 | 0.415 ± 0.052 |
| Cora | Historical | −0.052 | 0.088 | 0.035 ± 0.194 |
| Chameleon | Current | −0.299 | 0.114 | −0.011 ± 0.119 |
| Chameleon | Historical | 0.375 | −0.147 | 0.131 ± 0.143 |
On Cora’s current task, structural-state similarity was positively associated with transfer gain within rounds for all five seeds. The mean correlation was −0.024 when pooling observations across rounds within each seed. On Chameleon’s current task, the within-round association was near zero, and negative transfer occurred in 55.7% of pairs in the upper similarity quartile versus 10.0% in the lower quartile. For historical tasks on Chameleon, the corresponding rates were 39.3% and 72.0%. The signal with the highest within-round correlation depended on the dataset and task. Before server distillation, the mean validation cross-entropy of the three weighted aggregates differed by at most 0.0023 within any dataset and task group. Isolating the contribution of topology would require varying connectivity while holding features and labels fixed. Directly measuring gradient conflict would require gradient or update-vector alignment measurements.
Thank you for highlighting the distinction between structural similarity and transfer benefit. We will include the control settings and transfer analysis in the revised appendix.
3. Ablations of aggregation, teacher weighting, slot merging, and compression
The original ablations in Table 2 assess three contributions: coordinating clients through their structural states when local memory is available, retaining prior knowledge in a bounded buffer, and using the stored values in the current forward pass. We grouped aggregation and teacher weighting into the coordination module (A) because both use client states at the server. We grouped writing, merging, and compression into the memory evolution module (B) because these operations jointly determine what the buffer retains. Historical memory interaction (C) uses the retained values to augment current node representations. This decomposition also accounts for how the modules depend on each other. Removing A while retaining B and C tests server coordination with local retention and retrieval still available. Removing C while retaining B tests the added value of reading from a buffer that the client continues to maintain. Because C needs the slots produced by B, we compare the variants without C and without B and C to assess the effect of removing the evolving buffer when feature-level retrieval is already disabled.
The single-factor comparisons address the distinction you raised by isolating individual operations within A and B while keeping the rest of the method fixed. In A, state agreement can change the averaged model and key bank, and node-specific teacher weights can change the distillation signal. In B, a compatible new slot can update a historical slot even when there is room in the buffer, and compression determines how to fit the accumulated slots once capacity is exceeded. The task-boundary logs show when merging and compression were triggered, which determines when replacing either operation can affect the results. Single-factor experiments. We evaluated the four controls on the original task streams with five paired seeds per dataset.
-
State-aware aggregation. Equation (5) mixes the sample-count prior with normalized state agreement. Here counts task-visible nodes, and is the mean of over the other clients. Setting tests the role of state agreement in aggregation with the teacher weighting still active.
\omega_k=(1-\lambda_a)\pi_k+\lambda_a\frac{a_k}{\sum_\ell a_\ell}, \qquad (\boldsymbol{\theta}_g,\mathbf{K}_g)=\sum_k\omega_k(\boldsymbol{\theta}_k,\mathbf{K}_k). \tag{5}
-
Teacher weighting. Equation (6) weights each teacher by the overlap between its assignment for reference node and its current state. Uniform weights test whether this node-specific weighting adds value with state-aware aggregation and server distillation still active. b_{k,u}=\sum_p\sqrt{\widetilde q_{k,u,p}s_{k,p}}, \qquad \alpha_{k,u}=\frac{b_{k,u}}{\sum_\ell b_{\ell,u}}. \tag{6}
1. Controlled comparison with MOTION and POWER
We retained the baseline settings to document performance under the configurations used to reproduce or adapt each method. On Cora and CiteSeer, our MOTION reproduction used two clients, one new class per task, and one communication round with 50 local epochs per task. Keeping these settings preserved the graph partitions and task boundaries that determine what MOTION can coarsen and replay, as well as the synchronization schedule that shapes its conflict-aware updates. For FedAvg, FedDyn, and FedSSP, we retained the optimization schedules of our existing FCGL adaptations. This preserved both the amount of local training between synchronizations and the frequency with which the server combined updates, which together determine the optimization regime of each adaptation.
The original Cora and CiteSeer results for MemEvo-FCGL and POWER also came from different benchmark configurations. On Cora, the MemEvo-FCGL task builder kept only complete two-class groups, producing three tasks with exactly two new classes each. The POWER configuration retained the seventh class as a fourth task. That extra task expands the final label space and adds a training stage over which earlier classes must be retained. On CiteSeer, all six classes fit into three two-class tasks. The saved MemEvo-FCGL configuration used 10 communication rounds with three local epochs per round, and the POWER configuration used 15 rounds with five local epochs per round. This difference affects both the amount of local training and the number of server aggregations per task. The submitted paper disclosed these settings and used the unmatched results as references for their respective protocols, restricting its common-protocol conclusions to the matched subset.
Experiments under a shared protocol. We conducted a controlled comparison of MemEvo-FCGL, MOTION, and POWER on Cora and CiteSeer. For each of five paired seeds, the three methods shared the same three Louvain client partitions, class order, and 20/40/40 train/validation/test masks. All three used a GAT backbone and 15 communication rounds per task with five local epochs per round. The Cora experiment covers all seven classes across four tasks (2, 2, 2, and 1 classes), and the CiteSeer experiment covers six classes across three two-class tasks. Each method used its own memory configuration. A comparison under a common persistent-memory budget remains open.
We report final average accuracy (AM) and forgetting (FM) as mean ± standard deviation over the five seeds.
The main accuracy conclusion holds under the shared protocol. MemEvo-FCGL achieves the highest mean AM among the three methods on both datasets, exceeding MOTION by 3.62 percentage points on Cora and 11.85 on CiteSeer. MOTION has lower mean forgetting on CiteSeer. On the other six datasets, the reported results use common-protocol experiments for MOTION and archived experiments for MemEvo-FCGL and POWER.
Thank you for emphasizing the need for a controlled comparison. We have included the results obtained under the shared protocol in the revised appendix.