- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes AnyGRAM, a fully-inductive node classifier that separates transferable components learned across graphs from target graph-specific decisions based on target-graph support labels. To achieve this, it introduces rotation-invariant encoders with global covariance operators for cross-graph transfer, while making target-specific decisions through GCV-based ridge regularization selection and support-set cross-validation for branch selection. Trained solely on the Cora citation network, AnyGRAM achieves an average accuracy of 71.98% across 26 target graphs from various domain, exceeding the strongest existing fully-inductive baseline by 6.16 percentage points and outperforming GNN baselines trained separately on each target graph.
Critical strengths
S1. This paper tackles the important and challenging problem of fully inductive node classification, a key step toward developing general-purpose graph foundation models.
S2. The conceptual distinction between what should be learned across graphs and what should be learned directly from the target graph's labeled support set is intuitive and well-motivated.
Critical weaknesses
W1. Insufficient motivation and justification for the methodological complexity.
The proposed framework introduces several components without sufficient motivation. In particular, the rationale for selecting and combining the rotation-invariant input features is unclear. The learned fusion module is replaced by support-based branch selection at inference, yet uniform fusion during training achieves comparable performance (Table 2). Similarly, node-level overrides improve accuracy by only 0.1 percentage points. These results raise questions about whether the additional complexity is justified.
W2. Limited evidence for the benefits of global covariance propagation.
The paper presents global covariance propagation as a key contribution to overcoming the limitations of local operators. However, Table 2 shows that removing global covariance propagation reduces accuracy by only 0.3 percentage points, compared to a 2.2-point drop when removing the entire covariance branch family. These results provide limited evidence that global covariance propagation itself is a major contributor to the reported gains.
W3. Incomplete comparisons with recent fully-inductive and graph foundation models.
The experimental evaluation lacks comparisons with recent relevant approaches, including a recent fully-inductive baseline [1], and GFMs [2,3]. While their training and adaptation protocols differ, the paper should provide comparisons under compatible settings or clearly justify why such comparisons are not feasible.
[1] Lee et al., View Space: Learning Representation across Arbitrary Graphs, ICML 2026.
[2] Choi et al., Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors, ICLR 2026.
[3] Eremeev et al., GraphPFN: A Prior-Data Fitted Graph Foundation Model, ICML 2026.
Questions for authors
Q1. Could the authors clarify the motivation behind the specific choice of rotation-invariant inputs?
Q2. Why is the learned attention fusion module necessary during training if it is not used at inference time, especially given that uniform fusion achieves comparable performance?
Q3. How does the overall inference time scale with the number of support nodes and graph size? Could the authors provide runtime comparisons with existing baselines?
Q4. Could the authors provide comparisons with recent fully-inductive models and GFMs [1–3], or clearly justify why such comparisons are not feasible?
[1] Lee et al., View Space: Learning Representation across Arbitrary Graphs, ICML 2026.
[2] Choi et al., Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors, ICLR 2026.
[3] Eremeev et al., GraphPFN: A Prior-Data Fitted Graph Foundation Model, ICML 2026.
7 comments
Response to Reviewer Wry4 (Part 2)
Regarding the learned fusion and the node-level overrides (W1, Q2). Thank you for asking why the learned fusion is used in training. It has two roles. First, it is the training readout through which the task loss reaches the encoders, and for this role a uniform average gives a similar observed mean: trained with a uniform fusion, AnyGRAM reaches 72.04%, compared with 71.98% (Table 2). Second, it is the learned readout with which the paper tests its division, on exactly the same branch predictions (Table 2):
| Readout of the same branch predictions | Accuracy (%) |
|---|---|
| Hard attention routing (top-1) | 66.9 |
| Learned soft fusion | 69.5 |
| Uniform branch average | 70.0 |
| Per-node selection | 71.7 |
| Global selection by support CV | 71.9 |
| Global selection with node-level overrides (AnyGRAM) | 72.0 |
In these experiments, support-based branch selection outperforms the source-trained fusion on the same predictions, supporting the claim of Section 4.4. The node-level overrides address the difference between the per-node oracle, at 90.1%, and the per-graph oracle, at 72.7%: different branches succeed in different regions of one graph. Their margin rule is intended to reduce harmful node-level decisions: per-node selection without a margin is 0.2 points below global selection, while the overrides are 0.1 points above it. They also need no additional model evaluation, because they reuse the out-of-fold predictions of support CV. In the revision, Section 3.3 states both roles of the learned fusion, that a uniform training readout reaches a similar observed accuracy, and why the overrides use a margin.
Regarding the contribution of global covariance propagation (W2). Thank you for this question, which helped us locate where the global product contributes. Removing the covariance branches removes their inputs, encoders, and product together, while the second ablation keeps the inputs in and removes only the product . We now report the second ablation on each of the six graphs where support CV assigns at least 80% of the query nodes to covariance branches (Section 4.3), with five seeds (Table 12):
| Graph | AnyGRAM | Without the global product | Change |
|---|---|---|---|
| CiteSeer | 68.48 ± 3.73 | 60.92 ± 2.19 | −7.56* |
| full-DBLP | 73.84 ± 1.48 | 71.60 ± 2.97 | −2.23 |
| USA | 52.04 ± 2.38 | 51.21 ± 1.89 | −0.83 |
| Tolokers | 80.03 ± 0.17 | 80.15 ± 0.22 | +0.12 |
| Brazil | 65.38 ± 4.71 | 66.15 ± 4.21 | +0.77 |
| Europe | 49.63 ± 3.44 | 51.25 ± 4.03 | +1.62 |
| All 26 graphs (Table 2) | 71.98 | 71.67 | −0.31 |
*Uncorrected paired -test across five seeds: CiteSeer, ; full-DBLP, .
On CiteSeer and full-DBLP, support CV assigns 80% of the query nodes to global branches (Figure 3a), and removing the product lowers accuracy by 7.56 and 2.23 points. On Tolokers, the identity branch receives 89% of the query nodes, and on the airport graphs the selected branches include the identity branch; on these four graphs, removing the product changes accuracy by −0.83 to +1.62 points. On the other 20 graphs, the mean decreases by less than 0.01 points. These results locate the largest observed benefits of the global product on CiteSeer and full-DBLP, but do not uniquely attribute the remaining branch-family gain to individual input groups. The 0.31-point mean decrease over 26 graphs combines the decreases on CiteSeer and full-DBLP, the changes on the other four covariance graphs, and the nearly unchanged mean on the remaining 20. Its paired 95% confidence interval is points. Following your comment, Section 4.3 now reports the effect of the global product on CiteSeer and full-DBLP, and Appendix H gives the values for every graph.
Response to Reviewer Wry4 (Part 3)
Regarding comparisons with recent fully-inductive models and graph foundation models (W3, Q4). Thank you for naming these three models. Following your suggestion, we evaluated the released checkpoints of View Space [1] (RGVT with an MLP head), NodePFN [2], and GraphPFN [3] on the splits of Table 1, with the training split as the support set, the same test nodes, and five seeds (Table 7):
| Model | Pretraining | On the target graph | Graphs | Its accuracy | AnyGRAM |
|---|---|---|---|---|---|
| View Space | Arxiv | trains an MLP head; validation labels select the head and the depth | 25 | 72.29 ± 0.30 | 72.35 ± 0.56 |
| NodePFN | synthetic graph prior | support labels as context | 24 | 70.07 ± 0.52 | 72.79 ± 0.57 |
| GraphPFN | synthetic graph prior, LimiX initialization | support labels as context | 26 | 73.78 ± 0.40 | 71.98 ± 0.54 |
Each row uses the graphs that both models support: View Space is pretrained on Arxiv, which we exclude from its comparison, and in the evaluated configuration NodePFN supports up to 20 classes, which excludes Arxiv and full-Cora. NodePFN and GraphPFN run frozen with the support labels as context, as AnyGRAM does, while View Space trains a head on each target graph and selects it with validation labels. AnyGRAM, trained on Cora in 2.3 minutes, is close to View Space in observed mean accuracy (+0.06 points), above NodePFN by 2.72 points, and within 1.80 points of GraphPFN, which is pretrained on synthetic graphs starting from the tabular foundation model LimiX. Combining NodePFN's published accuracies on the 21 overlapping graphs with our reproduced accuracies on Wiki, BlogCatalog, and Roman-empire gives a descriptive hybrid average of 71.07% over 24 graphs. On the 21 overlaps, the published values average 1.14 points above our reproduction. This hybrid calculation is not a matched-protocol evaluation. In the revision, Section 4.2 compares AnyGRAM with these models, Appendix G gives their protocols and per-graph accuracies (Table 8), the abstract and Section 1 state the margin of AnyGRAM over the zero-shot baselines trained on the same source graph, and Section 2 now cites NodePFN [2].
A separate composition control preserves native GraphPFN predictions and adds the ten AnyGRAM branches as candidates for support-based selection. It reaches 74.73 ± 0.21% on the same 26 graphs and five seeds, with no target gradient updates (Appendix G). The standalone comparison above continues to use the submitted AnyGRAM.
Response to Reviewer Wry4 (Part 1)
Thank you for the detailed and specific review. We are glad that you found that the paper "tackles the important and challenging problem of fully inductive node classification, a key step toward developing general-purpose graph foundation models", and that the "conceptual distinction between what should be learned across graphs and what should be learned directly from the target graph's labeled support set is intuitive and well-motivated".
In short, your review asks whether each component of AnyGRAM is needed, and how AnyGRAM compares with recent fully-inductive models and graph foundation models in accuracy and cost. Following your comments, we:
Regarding the motivation of the rotation-invariant inputs (W1, Q1). We appreciate the question on why AnyGRAM uses these inputs. They follow from two requirements of the setting. First, no learned weight may have a shape that depends on the feature dimension d or the number of classes C, and thus the input width is fixed. Second, the input must stay the same when the projection is rotated: the projection is redrawn at every forward pass in training and averaged over 10 draws at inference, and an encoder that read Rˉ(p) would receive its input in a new basis at every draw. Every function of K(p)=Rˉ(p)Rˉ(p)⊤ meets the second requirement, and among these functions we use the parts whose width does not depend on the number of nodes: the diagonal of each K(p), which gives the propagated norms, and the columns of K(0) at L=16 landmark nodes. Two groups that do not depend on Ω complete the input: RWSE and log-degree, which give the identity and adjacency branches node descriptors on every graph, and the entropy, top-1 mass, and margin of the propagated support labels, which summarize the support labels with a width independent of C and stay the same when the classes are renamed. To address your question directly, we retrained AnyGRAM on Cora without each group, with five seeds (Table 11):
Removing each group lowers the observed mean accuracy by 0.62 to 0.77 points on the six graphs where support CV assigns at least 80% of the query nodes to covariance branches, but all paired 95% confidence intervals for the individual group removals include zero. Removing the whole branch family lowers accuracy by 2.17 points on the 26 graphs (p<0.05, Table 2). In the revision, Section 3.1 motivates each group using these two requirements, and Appendix H reports the ablations.