- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes a novel topological deep learning architecture combining two partially separate lines of works, persistent homology descriptors and learnable sheaf Laplacian, to achieve provably improved expressivity. In particular, the authors note that homology on different coefficients can be computed as cohomology over different cellular sheaves, opening an opportunity to combine these two approaches. Finally, the method is further improved by leveraging Sheaf Diffusion operators, typical in the sheaf neural networks literature.
Critical strengths
The manuscript is well written and motivated. The overall idea is interesting and, as far as I know, novel. The main construction is justified theoretically and empirically on synthetic graph data and some real banchmarks.
Critical weaknesses
While the paper is well written, I think a few details could be further clarified in the main manuscript.
In particular, my main doubt concerns Def. 3.4: do I understand correctly that this diagram is differentiable only with respect to the filtration times (via the birth and death indexes), but not with respect to the sheaf? How is the sheaf learnt then, when sheaf diffusion is not used? I see some argument in Apx. D.2 based on the spectral decorator (which is not explained much in the main paper), but it misses some details and arguments. Could the author clarify these aspects? In any case, I think differentiability is an important aspect that shouldn't be addressed only in the appendix, so I recommend the authors moving this discussion in the main manuscript.
Questions for authors
The example in the introduction showing the method can recover persisten homology on is simple but useful. However, I wonder if the authors can include some more complex examples, e.g. can we construct a sheaf s.t. its cohomology recovers the persistent homology in ?
Def 3.1: why is a needed in this definition?
End of page 4: what is ? Later is referred to as "eigenspace sum", does it refer to the space spanned by the selected eigenvectors?
Spectral connection above Eq. 3: why not sorting by eigenvalues? Also is referring to the graph Laplacian or does it also support Sheaf Laplacians?
Eq. 4: do you have any interpretation or intuition for what this resulting orthogonal connection represent?
Def 3.4: what does mean? this notation wasn't introduced earlier.
3 comments
Part 2/2
Def. 3.1: why is needed in this definition?
Thank you for pointing this out. The auxiliary graph is indeed unnecessary, since the connection can be defined directly on the input graph .
We have simplified Definition 3.1 accordingly, removing and making the corresponding notation changes in the compatibility proofs of Propositions 3.2 and 3.3. The revisions are highlighted in the manuscript, with the previous notation crossed out in red and the replacement shown in blue.
The revised definition now states the construction directly on .
What is ? Does it refer to the space spanned by the selected eigenvectors?
Yes. The space also provides the geometry underlying our spectral connection.
We regard as the space of real-valued functions defined on the vertices of the graph. The eigenvectors of the ordinary graph Laplacian describe different patterns of variation across the graph: smaller eigenvalues correspond to smoother functions, whereas larger eigenvalues correspond to functions that vary more strongly across adjacent vertices.
The space is the direct sum of the complete eigenspaces selected by our rule. If is an orthonormal basis of this space, then
gives the coordinates of the orthogonal projection of the indicator vector of vertex onto . In this way, the construction defines a spectral embedding , and the relative positions of these embedded vertices determine the orthogonal transports along the graph's edges.
We now define in Section 3.1 (blue).
Why not sort by eigenvalues? Is the graph Laplacian, or does it also support sheaf Laplacians?
Thank you for raising these two points. Our choice to order eigenspaces primarily by multiplicity is motivated by the computational cost of the resulting connection. Since the stalk dimension is the sum of the dimensions of the selected eigenspaces, choosing smaller eigenspaces first helps keep the sheaf Laplacian manageable.
More precisely, we order complete nonzero eigenspaces by increasing multiplicity, and use increasing eigenvalue to break ties. Importantly, we select entire eigenspaces rather than individual eigenvectors, because the latter are not uniquely determined within an eigenspace of repeated eigenvalue. This is also essential for the isomorphism compatibility established in Proposition 3.3.
The tie-breaking direction was incorrectly stated in the original Section 3.1, and we have corrected it in the revised manuscript. As discussed in our response to Reviewer KdH5, the corrected rule selects eigenvalue on SR25, consistently with Appendix B.7.
Here is the ordinary graph Laplacian introduced in Section 2; the sheaf Laplacian is denoted separately by .
Eq. 4: do you have any interpretation or intuition for what this resulting orthogonal connection represents?
The geometric interpretation helps explain why the spectral connection can distinguish graphs even when individual transports have the same rotation angle.
The main idea is to associate an oriented plane with every edge using the spectral embeddings of its endpoints. For an edge , the matrix is a skew-symmetric generator of rotations in the two-dimensional plane spanned by and .
Consequently, the transport
performs a rotation by in this plane, while acting as the identity on its orthogonal complement.
An interesting consequence is that every individual edge transport has the same eigenvalues: , , and with multiplicity . Therefore, the distinguishing information does not come from changing the rotation angle or the eigenvalues of individual transports.
Instead, it comes from how the rotation planes are oriented relative to one another across the graph. When these transports are composed along cycles, their relative orientations determine the resulting holonomy and influence the spectrum of the sheaf Laplacian. This provides a geometric explanation for why the construction can capture structural information that is absent from the ordinary graph Laplacian spectrum.
We have added this interpretation after Eq. (4) in Section 3.1 (blue).
Def. 3.4: what does mean? This notation was not introduced earlier.
Thank you for noting the missing definition. The notation denotes the multiset of strictly positive eigenvalues of , including their multiplicities.
We have made this explicit in Definition 3.4 (new text in blue), so the notation is introduced before being used in the descriptor.
We like to thank the reviewer once again for the valuable contribution. We firmly believe that the presentation quality of the paper is much better with these additions.
I thank the authors for the detailed answers, which clarified most of my doubts.
I recommend the authors to explicitly clarify the persistent homology path does do not provide gradients to learn the sheaf Laplacian, which instead come only through the spectral decorations (this seems still a bit implicit in the paragraph at the end of Sec 3.2).
Regarding this question:
Can we construct a sheaf such that its cohomology recovers the persistent homology in Z2?
Thanks for the answer, but this doesn't clarify how that can be represented by the Sheaf Laplacians learnt by your networks right? The stalks are in R^n, how can the network learn to produce this sheaf such that its cohomology recovers the persistent homology of ? I think aspects about what sheaves and persistent homologies can be actually parameterized by the network need some further discussion in the paper.
I think the authors can clarify these points directly in the final manuscript, so I maintain my positive recommendation.
Part 1/2
We are grateful for your careful reading of our manuscript and for the constructive suggestions regarding its presentation. Several of the points you raised were either discussed only in the appendix or left implicit in the main text, and we agree that they deserve clearer explanations. Following your feedback, we have expanded the discussion of differentiability in Section 3.2 and clarified the notation and interpretation of the spectral connection in Section 3.1. We address your questions below and would be happy to discuss any remaining concerns.
Thank you for raising this question. The sheaf is indeed learned through the spectral decorations, even when sheaf diffusion is not used. Your reading is correct regarding the discrete nature of persistence pairing, but there is an additional gradient path through the sheaf Laplacian that could have been better explained in the main manuscript.
More precisely, the selection of birth–death pairs is a discrete operation, and we do not differentiate through this combinatorial pairing. Once the persistence events are fixed, their filtration coordinates remain differentiable with respect to the learned filtration functions fV and fE.
The important distinction is that the connection parameters receive gradients independently through the spectral coordinate of Definition 3.4. For each persistence event, we construct the sheaf Laplacian from the learned transports Ru→v of Eq. (2). Since the matrix LF(R)=δ(R)⊤δ(R) depends on these transports, changes to the connection affect its eigenvalues and consequently the output of the spectral readout.
For a simple eigenvalue λi with normalized eigenvector qi, its derivative satisfies
dλi=qi⊤(dLF)qi.
This expression does not require differentiating the eigenvector. As in SpectRe, the spectral decoration retains the positive eigenvalues, including their multiplicities, alongside the persistence coordinates. ShePHerD uses the sheaf Laplacian in place of the ordinary graph Laplacian. Since eigenvalues are independent of the choice of eigenvector basis, the descriptor remains well-defined even when eigenvalues repeat. Wherever the selected spectrum is differentiable, its dependence on the learned transports provides a gradient path to the connection parameters, even without sheaf diffusion.
Following your recommendation, we have added a dedicated paragraph entitled "Differentiability" in Section 3.2, immediately following the definition of the descriptor (new text in blue). To complement the explanation, Appendix D.2 now includes a numerical gradient check.
The persistence events determine which features are represented, while the spectral decorations provide a differentiable route for learning the sheaf.
Yes, and we appreciate the suggestion to make the relationship between ordinary persistence and sheaf cohomology more explicit.
A simple construction is the constant cellular sheaf F2, where F2=Z2. We assign the vector space F2 to every vertex and edge, and take all restriction maps to be the identity.
Under this choice, the sheaf coboundary is precisely the graph incidence matrix computed modulo 2. Since −1=1 in F2, the signs associated with edge orientations coincide. Consequently, the resulting cellular sheaf cohomology is ordinary graph cohomology with coefficients in F2.
The same construction can be applied consistently at every level of a graph filtration. By the correspondence between homology and cohomology over a field, the resulting persistent cohomology has the same interval decomposition as ordinary persistent homology over F2.
This example follows from the constant-sheaf construction and the universal coefficient results discussed in Appendix A. It also helps clarify an important aspect of our contribution: while a constant sheaf recovers an ordinary coefficient system, our real-valued learned SO(d) connections allow the restriction maps themselves to vary, thereby changing the resulting cohomological information.