- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces Hierarchical Sheaf Pooling (HiSP), a pooling operator for neural sheaf diffusion. Following the Select–Reduce–Connect framework, it partitions the graph into connected clusters, constructs regularised transport maps from the learned restriction maps along rooted spanning trees, and aggregates node features after mapping them into a common reference stalk. A new sheaf Laplacian is learned on the resulting coarse graph. The authors also introduce a sheaf-aware readout for graph-level prediction.
Critical strengths
- The problem of aggregating sheaf-valued signals across graph resolutions is interesting and relevant to hierarchical graph representation learning. The transport-based reduction is a concrete, mathematically motivated way to make features in different stalks comparable.
- The construction is explained in reasonable mathematical detail, including regularised least-squares transport, non-expansive normalisation, and an explicit discussion of path and root dependence.
- Several controlled experiments show substantial gains over unpooled neural sheaf diffusion.
Critical weaknesses
- The methodological novelty and necessity of the proposed complexity are insufficiently established. The paper combines standard graph coarsening, established neural sheaf diffusion, regularised inverse maps and a new readout; the specific advantage of sheaf-based transport over simpler aligned or learned feature reductions remains unclear.
- The choice of baselines is too limited to substantiate claims about hierarchical learning. On several tasks, the comparison is principally with unpooled NSD and GCN/GIN equipped with EigenPooling. Comparisons against a broader range of hierarchical GNN pooling methods, and especially stronger controls using the same selection and readout but simpler reductions, would be important.
- Several synthetic tasks are constructed around the intended hierarchical mechanism. In HierBI, the four connected rooms and the target number of clusters are built into the pooling setup, making it difficult to separate the effectiveness of transport from a favourable prescribed hierarchy. The study does not sufficiently test robustness to other graph structures or imperfect cluster assignments.
- The empirical benefit on standard datasets is mixed, which is particularly important for assessing the need for hierarchical pooling. In Table 6, adding HiSP pooling to NSD with the proposed HiSP readout improves MUTAG (79.9±11.2 to 82.5±5.1) and PROTEINS (69.9±4.2 to 74.4±4.1), but not ENZYMES (41.0±5.7 to 37.8±6.4) or NCI1 (74.6±4.1 to 74.2±3.0). Given the variability, the evidence that the pooling step itself yields a reliable improvement is limited. Node-classification results are likewise largely comparable to the unpooled network, rather than consistently better.
- The reduction depends on choices of cluster roots, spanning trees, and regularisation/normalisation parameters. While the paper acknowledges root and path dependence (Section 3.3.3 and Section 5), it provides insufficient experimental evidence of predictive stability. Ideally, variability across these choices should be quantified and compared with variation across random seeds and data splits. Moreover, non-expansive edge transports may attenuate contributions from nodes far from the root, introducing a potentially consequential dependence on cluster geometry.
- The real-world VoteView task still relies on a constructed topology and predetermined community structure, limiting how strongly it validates generalisation to naturally occurring hierarchies. The construction of the vote-specific cutting point used in node features should also be clarified, including what information is available at prediction time.
There are also minor but worthwhile presentation issues. Section 4.1 contains awkward or insufficiently precise claims (for example, that “the label lives at a coarser sheaf resolution” or that a fine sheaf has “no place to represent the coarse constraint”). Several experimental captions could better define the setup and notation, such as the meaning of boldface in Table 4 and the interpretation of pooling “stages”. The conclusion mixes implementation details, architectural descriptions and experimental claims rather than succinctly identifying the main findings and limitations; its organisation could be improved. Some terminology, such as “distractor-rich regions” and “branch embedding”, would also benefit from clarification.
Overall, the current empirical study does not yet provide sufficient evidence of the robustness, reliability, and generalisability of the proposed method to other datasets where hierarchy is important. The strongest improvements concentrate on controlled synthetic tasks with favourable coarsening structures; broader comparisons and quantitative sensitivity analyses would be needed to justify the method's additional complexity.
Questions for authors
- Can the authors isolate the contribution of sheaf-based transport from the benefits of grouping nodes and using the new readout? In particular, does alignment through restriction-map transports outperform mapping each stalk into a shared feature space using learnable projections, followed by pooling, under otherwise matched architectural and training choices? Such a comparison should extend beyond HierBI to multiple datasets.
- Why was EigenPooling selected as the principal hierarchical GNN baseline? Could a broader comparison with established graph pooling methods be provided, especially on LRIM, VoteView, and standard graph-classification benchmarks?
- Section 3.3.3, lines 239–241: the statement that two different paths can connect a cluster root to the same vertex is potentially confusing, since a fixed spanning tree contains a unique path between them. More importantly, how do accuracy and variance change across root choices, spanning trees, tree resampling, transport path length? Can this sensitivity be compared quantitatively to variance across seeds or data splits?
- For HierBI, how much prior structural information is given to SELECT (including the prescribed K=4)? How are the hidden signs assigned, and does performance persist when clusters do not coincide with the four planted rooms? Could the authors test less constrained or noisier hierarchical structures?
5 comments
Response QYyF Weaknesses 5 and 6
Weakness 5 — Root choice and tree sampling
On HierBI we ablate the two choices. Spanning-tree sampling, with the root fixed at the maximum-degree hub, is Appendix D.6, Table 18:
| Tree sampling | Test accuracy (%) |
|---|---|
| Random BFS (default, ) | |
| Deterministic BFS | |
| Tree ensemble () |
Root selection, with random BFS held fixed, is Appendix D.6, Table 20:
| Root selection | Test accuracy (%) |
|---|---|
| Max-degree root (default) | |
| Min-degree root | |
| Random root per cluster |
Section 3.2 fixes the root as the maximum-degree hub in each cluster. The hub is read off the graph, so the rooted trees are built once and cached with the partition (Section 4.8). The three tree samplings stay within about one point. On the trained HierBI checkpoints we keep the hub root and redraw random BFS trees per test graph. The mean of those per-checkpoint standard deviations of test accuracy is percentage points, an order of magnitude below the inter-seed variation of –. That sentence is in Appendix D.6.
Weakness 6 — VoteView
The four wings are how the graph and the label are built. They are not fed as clusters. SEL is the connected partition of the adjacency with (Section 4.5, Appendix D.3); the wings are not read by that selector. Features are , and ballots are labels only.
On the remaining presentation points:
- In Section 4.5 and Appendix D.3, we clarified that in the NOMINATE spatial voting model (Poole & Rosenthal, 1985), each senator has a static 2D ideological coordinate for a given Congress, and each roll-call bill has a 2D cutting midpoint representing the ideological midpoint of the bill topic under debate. At prediction time, vertex features are (with a fraction of senators randomly negated in Table 5); individual senator ballots are never used as input features, and the model must infer the four-wing coalition pattern solely from noisy ideological positions relative to the bill topic.
- In Section 4.1, we replaced the phrasing “the label lives at a coarser sheaf resolution” with a direct statement that the graph label depends on coarse inter-community relationships that differ from the fine intra-community relationships on the input edges, and specified the exact room and length- corridor construction.
- In Section 4.4 (Table 4) and Appendix D.8 (Tables 25–26), we explicitly stated the pooling configuration and the boldface convention.
- In Sections 3.6 and 4.3, we defined the three per-cluster descriptor branch embeddings () and the on-path wrong-class distractor nodes at first appearance.
- The organization of Section 4.5 was improved.
Response QYyF Questions
Question 1
To isolate the contribution of sheaf-based transport from the grouping of nodes and from the new readout, the partition and the decoder are held fixed. Sheaf transport is replaced by one shared residual MLP that maps every node into one coordinate space before pooling. The MLP does not use the restriction maps. Its last layer starts at zero, so at initialization the pooling step is a coordinate-wise mean, and training is free to leave that mean. The comparison is on HierBI, Marked PathCopy, and VoteView (Appendix D.6, Table 19).
| Alignment | HierBI | Marked PathCopy | VoteView |
|---|---|---|---|
| Shared MLP | |||
| Damped pseudoinverse () | |||
| Adjoint transport () |
On HierBI and Marked PathCopy the clusters are the same in every row, so the gap is the alignment. Adjoint transport uses the learned restriction maps; the shared MLP does not. On VoteView the features are already positions in one Euclidean space, and the shared MLP reaches the same accuracy as adjoint transport. Sheaf-aware transport is necessary when the task needs that alignment, which is the setting in which a sheaf network is needed in the first place.
Question 2
In the revised version we compare multiple poolers (EigenPool, MIS, TopKPool, SAGPool, MinCutPool, and DiffPool) on GCN, GIN, and NSD. The readouts are a global mean, SheafPool, and the HiSP readout. The full grids are in Section 4 and in Appendix D. On LRIM-16-hard the broadened comparison is NSD, BuNN, and CSNN, each with and without HiSP (Section 4.4, Table 4; Appendix D.8, Table 25).
Question 3
In Section 3.3.3 the sentence now reads: “Within a cluster, two different paths and stemming from distinct spanning trees may connect the root to the same node .” About root choice and tree sampling, see Weakness 5.
Question 4
See Weakness 3.
Response QYyF Weaknesses 1,2,3 and 4
We thank Reviewer QYyF for the detailed methodological feedback and presentation suggestions. Below we address each weakness and question point by point, referencing the corresponding sections and tables in the revised manuscript.
Weakness 1 — Sheaf-aware hierarchical pooling
HiSP is the first sheaf-aware hierarchical pooling operator for SNNs. It introduces a new architectural capability: using learned sheaf relations to construct coarse entities, then learning new relations between those entities at the next resolution. Existing sheaf diffusion layers and global readouts do not provide this hierarchy.
The methodological novelty is deriving the reduction from the learned restriction maps, transporting node representations into a common cluster stalk before aggregation. Standard clustering and regularized inversion are building blocks used to define this previously missing operation.
Its empirical contribution is also isolated: with the partition and readout held fixed, replacing ordinary averaging with HiSP raises significantly improve performance in tasks such HierBi, which demonstrates the value of the new reduction beyond the choice of clusters or readout.
Weakness 2 — Choice of baselines
We have added a broader set of hierarchical pooling baselines to the revised version.
The poolers are EigenPool, κ-MIS, TopKPool, SAGPool, MinCutPool, and DiffPool, on GCN, GIN, and NSD. The readouts are a global mean, SheafPool, and the HiSP readout. The full grids are in Section 4 and in Appendix D.
We also add two stronger sheaf backbones, BuNN and CSNN, each with and without HiSP, on LRIM-16-hard (Section 4.4, Table 4; Appendix D.8, Table 25). HiSP still improves both at the longest tested depth.
The control that keeps the selection and the readout fixed, and simplifies only the reduction, is also in the revision. The partition and the decoder stay fixed. Sheaf transport is replaced by a coordinate-wise mean or by one shared MLP that does not use the restriction maps. That comparison is on HierBI, Marked PathCopy, and VoteView (Appendix D.6, Table 19). Results show that sheaf-aware transport is necessary when the task needs that alignment, which is the setting in which a sheaf network is needed in the first place.
Weakness 3 — Given hierarchy, cluster count, and imperfect clusters
The concern is that HierBI builds the four rooms and the target number of clusters into the setup, so the transport cannot be separated from a favourable prescribed hierarchy, and that other cluster counts and imperfect assignments are not tested.
The planted hierarchy is not given to
SEL. It receives only the unlabeled adjacency matrix A. Node indices are randomly permuted. Room labels, corridor indicators, and the hidden signs are never input features (Section 4.1 and Appendix D.2). Setting K=4 chooses a count. It does not assign nodes to the four rooms.The number of clusters is not fixed at that count. κ-MIS (Bacciu et al., 2023) sets K from the graph and is not told that there are four rooms. At κ=3 it matches the run that was given K=4 (Appendix D.6, Table 21).
Furthermore, those κ-MIS clusters are imperfect relative to the planted rooms: they split rooms and corridors instead of recovering the four rooms. Sheaf transport still carries the label on that assignment. A standard pooler on the same imperfect partition does not. The result is the transport under a topological partition, including a partition whose size was not prescribed and a partition that misses the planted rooms.
Weakness 4 — When the pooling step helps
The concern is that the gain on standard datasets is mixed, so the pooling step itself may not be a reliable improvement, and that node classification stays close to unpooled NSD rather than consistently beating it.
HiSP makes interactions between groups of nodes easier to learn. Pooling also compresses information, so its benefit depends on whether those interactions outweigh losing fine detail. This is particularly relevant to node classification, where fine-resolution skip features may already provide sufficient predictive information, leaving limited benefit from the coarse branch (Appendix D.7, Table 24).
The benefit of hierarchy is clear on LRIM. With the same sheaf parameterization and total layer budget, two-stage HiSP improves over NSD at every tested depth (Section 4.4, Table 4).
On standard graph classification, the results show a task-dependent benefit (Section 4.6, Table 6). MUTAG and PROTEINS improve when the pooling stage is added on top of the HiSP readout. On ENZYMES and NCI1 the gain over SheafPool is the readout, and a pooling stage is not required. The mixed standard-benchmark results clarify where this additional hierarchy currently offers value.