- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a Lie-algebraic framework for unifying factual and counterfactual GNN explanations. It learns low-rank generators to produce label-preserving and label-altering transformations in a frozen latent space, with a coefficient network controlling the transformation magnitude. The authors evaluate on five graph datasets, report ablation studies, and include assumption-check experiments.
Critical strengths
The paper presents a detailed pipeline combining low-rank latent transformations, coefficient prediction, and staged training for factual and counterfactual explanations.
Critical weaknesses
Definition 1 appears not to define a subgroup. Label preservation at a single point is not closed under composition, and at a strict-margin sample the set contains a neighborhood of the identity, so its tangent space becomes the entire Lie algebra. This leaves no nontrivial one-dimensional counterfactual complement, which directly affects the claimed decomposition and the completeness argument of Theorem 2.
I also note that the mechanism experiments mainly measure boundary-crossing and sparsity behavior, which reflect properties of the training protocol rather than the structural conditions assumed in the theorems. They are useful diagnostics, but they do not provide independent validation of the theoretical claims.
Overall, the ambition of this work is a strength. Connecting representation-space transformations with factual and counterfactual explanations through Lie-theoretic structure is an intellectually compelling direction. However, I would appreciate clarification on the foundational issues identified above.
Questions for authors
For a point with a strict classification margin, how can a nontrivial factual subalgebra and a one-dimensional counterfactual complement arise, and how does this affect the completeness claim in Theorem 2 and the minimal-generator claim in Theorem 4?
7 comments
Response to Reviewer eDXv part 2 of 2
(Response to reviewer eDXv part 2/2)
W1.3 (Theorems 2 and 4)
We will restate this as completeness under the orbit, not over every point. The factual flows reach every point of the local orbit , not every nearby point of . When is injective on , this orbit is an immersed submanifold of dimension . It covers the level set of y only if , which our K-generator span does not satisfy. The foliation itself is by level sets of y and needs no group structure.
Theorem 4. Its form is unaffected. It uses only , which now follows from . It remains a first-order statement restricted to one-hot coefficients (Section 8).
W2 (Mechanism experiments)
Our theorems are conditional statements. Given their hypotheses, the conclusions follow by proof and need no empirical validation. The hypotheses are first-order tangency of the factual generators, bracket closure, the reductive condition, and concentrated (one-hot) coefficients. What can fail in practice is whether a trained model satisfies those hypotheses.
GLIDE is designed so that it has the following properties, and as per Table 4, each loss term enforces one condition:
-
enforces tangency, .
-
enforces bracket closure of the factual span.
-
enforces the reductive condition .
-
encourages the concentrated coefficients assumed by Thm. 4.
-
enforces the label flip of Def. 3.
The mechanism experiments verify that this construction succeeds. The hypotheses check that the learned generators meet the theorems' hypotheses on held-out test graphs, where they were not optimized. They are not independent evidence for the theorems themselves, but they show that we are indeed operating under this setting.
We hope this review answers all of the reviewer's concerns, and we are happy to address any remaining questions during the discussion period.
I appreciate the corrections, but they have not resolved my concerns. I am lowering my rating to clear rejection.
My main concern is that the authors have weakened the theoretical results without reconsidering the claims built on them. The subgroup has become a first-order kernel, completeness has been restricted, and manifold preservation has become a displacement bound. These changes affect the substance of the contribution. The revised paper still needs to show why the remaining results support its claims about explanation quality.
There are also unresolved contradictions. Definition 1 says that is not a subgroup, yet the next paragraph identifies its connected component's tangent space with the factual Lie algebra. Corollary 1 still uses as a homogeneous space (pp. 3-5). At a strict-margin point, contains an open neighborhood of the identity, so its tangent space is the full algebra. Separately, the first-order tangency in Proposition 1 does not guarantee margin preservation along finite exponential flows. I recognize that the new displacement bounds are tighter. This does not answer the manifold concern. They bound distance from the original embedding, and even an arbitrarily small displacement can leave the data manifold. Making this bound tighter cannot establish manifold membership or the claimed control of OOD drift. Without an additional argument linking displacement to data validity, those claims need to be withdrawn and the narrower contribution evaluated on its own merits.
The response about mechanism experiments also misses my concern. I am not asking for empirical proof of a theorem. Checking assumptions on held-out data is useful, but training penalties do not guarantee that the assumptions hold exactly. The paper needs to account for the remaining errors. Likewise, observing sparsity after hard top-1 masking does not show that the selected generator minimizes displacement. Removing a loss term can show that it helps, but does not by itself explain whether the gain comes from the proposed geometry or ordinary regularization.
Theorem 4 is another example. It assumes geometric convergence and then derives convergence of the displacement quantities. The decreasing envelopes do not mean that the actual displacement or computed bounds decrease during training. Lemma 2 gives sufficient conditions involving local strong convexity, fixed generator selection, and full-batch gradient descent. These have not been established for the actual mini-batch Adam training on low-rank factors with a straight-through Gumbel mask. The result therefore does not explain why the implemented training should behave as claimed.
The response still leaves unclear how a fair comparison with the baselines was ensured and whether the results were rechecked after the evaluation code was corrected. The metrics themselves also need care. Zero generators give Fid+ = 0 and Fid- equal to the original prediction confidence, so a confident classifier can score very well without producing a meaningful explanation. The motif results are useful, but do not settle this concern about the broader comparisons.
These issues require more than another clarification of the definitions. The authors need to rebuild the paper around the claims they can support and design experiments that test those claims.
Response to Reviewer eDXv part 1 of 2
(Response to reviewer eDXv part 1/2)
We thank the reviewer for their constructive feedback and precise questions. We appreciate that the reviewer found our pipeline, which combines low-rank latent transformations, coefficient prediction, and staged training for factual and counterfactual explanations, detailed, and that they considered the ambition of the work a strength, describing the connection between representation-space transformations and factual and counterfactual explanations through Lie-theoretic structure as an intellectually compelling and ambitious direction. We address each point below, and have marked all corresponding updates in blue in the revised manuscript.
W1.1 (Definition 1 appears not to define a subgroup)
The reviewer is correct that Hz is not a subgroup. We did in fact initially have a paragraph discussing that Hz is not formally a subgroup because it is not closed, etc., however it was commented out by mistake due to space constraints and as a result this confusion has persisted and affected the “soundness” evaluation of the paper. We apologize for this, and for the incorrect use of the term; in fact we do not need any closure guarantees. This is both correct and by design, and it does not affect the decomposition or any downstream results because none of these use or need subgroup properties. Hz is not intended to be a subgroup, nor does it need to be. Hz=g:y^(g⋅z)=y^(z) is the preimage of the class region under the orbit map g↦g⋅z. Membership of g1 is tested at z and we do not claim that it also applies at g2⋅z. Hz can be understood as the set of label-preserving transformations of one sample (the latent representation z of an input graph x). This does not mean that it is a symmetry group of the classifier as a whole.
Moreover, we do not want Hz to be a subgroup because at a strict margin z, Hz contains an open neighborhood U of e. A subgroup containing U contains the identity component G0, which is generated by U. If Hz were then to be a subgroup, every g∈G0 would preserve the label y^(z), making no counterfactual reachable. As such, Hz can only be a true subgroup when there is only one class (nothing to explain).
Hz also does not need to be a subgroup for any of our results. The closure is not necessary for our method, theoretical results, or interpretability claims. The method uses only the linear subspace hz=kerℓz and the flows t↦exp(tX)z, which are one-parameter subgroups of G, not of Hz.
The codimension-one decomposition is proved independently. Lemma 1 gives dimkerℓz=dimg−1 from Assumption 1 (ℓz≡0) alone. It does not use subgroups, faithfulness, or surjectivity assumptions. Equation 4 decomposes g=kerℓz⊕mz from it, and training targets kerℓz directly with Ltan.
For Theorems 1 and 2, the local factorization g=exp(Xfact)exp(Xcf) holds for any complementary pair (inverse function theorem), so it needs no subgroup. Reductivity is a property of the learned span that is enforced by Lclosure and Ladj. kerℓz does not need bracket closure in general. The leaves of Theorem 2 are the level sets of y that foliate Zy (without any group structure). We will restate completeness only for exp(hz)z rather than for the entire set.
Theorems 3 – 5 and Propositions 2 – 3 do not use Hz. Theorem 2 has been restated by level sets of y and this does not need group structure.
W1.2 (Where the nontrivial factual subalgebra and 1-D complement come from)
They come from the logit level set Lz=g:y(g⋅z)=y(z)⊂Hz, not from TeHz.
Let F(g) = y(g \cdot z). Since dFe=ℓz=0, the regular value theorem makes Lz a codimension-one submanifold near e, with TeLz=kerℓz=:hz. So mz=hz⊥ is one-dimensional. Elements of hz preserve the logit to first order, y(exp(tX)z−y(z)=O(t2), and hence preserve the label for small t. mz is the unique first-order logit-changing direction. The revision will define hz this way and Proposition 1's faithfulness and local-transitivity hypotheses are replaced by ℓz≡0.