- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes SL(n) as a single latent representation space built on the special linear group with a left-invariant Schatten-p tangent norm. The authors argue that existing mixed-curvature product manifolds suffer from two limitations: the factor decomposition must be predetermined, and product metrics have vanishing mixed sectional curvature so curvature regimes do not interact across factors. They prove SL(n) exhibits pointwise positive, zero, and negative flag curvature around a common flagpole, with asymptotically maximal mixed-curvature and coupling capacities, and its non-nilpotent Lie algebra supports arbitrarily deep nested Lie brackets. Experiments on graph metric reconstruction, large-scale link prediction, and order-sensitive composition report consistent improvements over geometric baselines.
Critical strengths
-
The paper identifies a real, provable limitation of product metrics (vanishing mixed sectional curvature) and builds a single manifold that circumvents it.
-
The order-sensitive composition experiment compares SL(4) against Heisenberg and triangular groups with finite composition depth. The performance ordering is consistent with depth ordering, isolating an algebraic property from a geometric one.
Critical weaknesses
-
The claim about product metrics (vanishing mixed sectional curvature) is correct, but prior work explicitly studies geometry interaction. CurvRec (SIGIR 2023) uses curvature-aware geodesic distances to maximize mutual information between Euclidean and non-Euclidean spaces, stating message passing is hindered without interaction. GIE (AAAI 2022) proposes geometry interaction across Euclidean, hyperbolic, and hyperspherical spaces. MKRec (2024) transfers geometric information between manifold spaces. These operate at the representational level rather than the curvature-operator level, but the paper neither cites them nor distinguishes its "coupling" from their "interaction." A claim of first genuine interaction cannot omit published work on exactly that.
-
Main experiments use Exp-AdamW for SL(n) while manifold baselines use standard optimization. The Riem-AdamW control shows Exp-AdamW is better for SL(n), not that all geometries were equally optimized. A matched-parameterization comparison is needed. No wall-clock or memory comparison is reported, so the practical significance of the gains cannot be assessed.
-
No experiment isolates coupling from mixed curvature. The claim that coupling drives gains rests on indirect evidence. A matched-capacity baseline with zeroed cross-sign interaction is needed.
-
The semidistance is a non-metric surrogate. Local tightness and path-refinement are shown only on a 64-node KEGG subgraph. Adequacy on OGBL-PPA and HumanCyc is unverified. Using a non-metric objective on the largest experiment deserves more than an appendix subsection.
Questions for authors
-
The paper states product mixed-curvature spaces have “no genuine interaction.” How does this relate to CurvRec (SIGIR 2023), GIE (AAAI 2022), and MKRec (2024), which explicitly model interaction between curved manifolds? If the distinction is representational vs. curvature-theoretic, please state it explicitly in the main text. If these are not considered relevant, explain why.
-
Can you provide a controlled comparison where all geometries—including product manifolds, SPD, Grassmann, and Siegel—are optimized under a matched parameterization and learning-rate protocol? If rankings change under matched optimization, what does that imply for attribution of gains to geometry?
-
Report wall-clock time per update, peak GPU memory, and total training time for SL(8) versus the strongest vector baseline on OGBL-PPA.
-
Provide branch-margin distributions, fraction outside the principal-log domain, and comparison against K=4 or K=8 path approximations for HumanCyc and OGBL-PPA.
-
Design an experiment that isolates coupling from mixed curvature, e.g., a variant retaining positive and negative eigenspaces but suppressing cross-sign curvature interaction.
4 comments
Q4(&W4): Numerical Validity of the Semidistance on Large-Scale Data:
Thank you very much for this question. We have added verification on all three datasets. For Principal-logarithm domain: All of the millions of relative matrices checked on the three datasets lie in the principal-logarithm domain, with minimum branch margins of 0.83–2.97 rad, and no NaN or Inf values occur. For Path approximation: We perform end-to-end training with path segments as the objective, and measure the gap on 100 randomly sampled pairs for each learned embedding. The relative gap between the semidistance and the reference is only 1.4%–2.1%, and the change in downstream performance is at most 0.5%, which is far smaller than the standard deviation.
These results have been added to the revised version (p. [18–19], Fig. 7).
Theoretical guarantee: As proven in Lemma B.1 of the original paper, is exactly the length measured along the standard exponential path. It is therefore always an upper bound on the intrinsic distance, and locally it agrees with the intrinsic distance up to second order, with errors only in higher-order terms; the closer the points, the more accurate the approximation. is nonnegative, symmetric, and separates distinct points, and only the triangle inequality is not guaranteed. Such distances are common in representation learning: for example, the squared Euclidean distance and the squared Lorentzian distance in hyperbolic representation learning [1] do not satisfy the triangle inequality in any space with midpoints, yet they are widely used as optimization objectives. Moreover, as shown above, the relative gap between and the refined path distance is only about 2%, so the practical effect of the missing triangle inequality is negligible.
Q5(&W3): Isolating Curvature Coupling from Mixed Curvature:
Thank you very much for this question, which is one of the most important questions for our work! We first clarify that the product-manifold baselines in the original paper (e.g., ) already have mixed curvature without coupling [3], and outperforms them on all tasks. However, their parameterization differs from that of , so we added a strictly matched decoupled control.
In the ablation, we use the fact that every invertible matrix has a unique polar decomposition , where is orthogonal and is symmetric positive definite [2]. Since and , we have , i.e., and . We equip with the product metric. provides nonnegative curvature and provides nonpositive curvature, so both the positive and negative curvature eigenspaces are kept. However, the curvature tensor of a product metric is block-diagonal, so the sectional curvature across the two factors is always zero and there is no coupling [3]. This is exactly the variant you described. It shares the same parameters, dimension, optimizer, and objective with the full model (), and differs only in whether coupling exists.
| Dataset | Metric | w/o Curvature Coupling | (Full) |
|---|---|---|---|
| KEGG | Avg. Distortion ↓ | 0.0805 | 0.0366 |
| KEGG | High-related ↓ | 0.1091 | 0.0430 |
| HumanCyc | Avg. Distortion ↓ | 0.0523 | 0.0316 |
| HumanCyc | High-related ↓ | 0.0550 | 0.0331 |
| OGBL-PPA | Hits@20 ↑ | 0.1124 | 0.1229 |
These results show that mixed curvature without coupling does not bring improvement, and the gains come from intrinsic coupling, especially in regions with high curvature mixture. We also performed an additional flat ablation that removes the nonlinear Lie group structure. The full ablation study is on p. [10] of the revised version.
Finally, we thank you again for your patient reading and your insightful and valuable comments! Your comments have made this work more complete, and we hope that this work, improved together with your help, can bring some inspiration and contribution to the community.
[1]Law et al. (2019), Lorentzian Distance Learning for Hyperbolic Representations. ICML 2019.
[2]Higham (2008), Functions of Matrices: Theory and Computation. SIAM.
[3]Sáez de Ocáriz Borde (2026), On the Expressive Power of Mixed-Curvature Representations in Product Manifolds. Workshop on Geometry-grounded Representation Learning and Generative Modeling at ICLR 2026.
Thank you for the detailed response. I have raised my score to 3 (Weak Acceptance).
Dear Reviewer WBHv,
Thank you very much for taking the time to evaluate our rebuttal. We are glad that our responses addressed your concerns, and we are sincerely grateful for your decision to raise the score.
We are also grateful for the time and care you devoted to reviewing our paper and helping us improve it! We will incorporate your suggestions into the final version, and we hope that this work, strengthened by your feedback, will bring some meaningful inspiration and contributions to the community.
Best regards,
The Authors
Response to Reviewer WBHv
First and foremost, we sincerely thank the reviewer WBHv for the patient reading of our work and the insightful and constructive comments! We provide our detailed responses below:
Q1(&W1): Relation to Representation Level Geometry Interaction (CurvRec, GIE, MKRec):
Thank you for this question and your broad reading of the literature! We have added citations to these works in the revised version, and we clarify that "coupling" in our paper refers specifically to the curvature operator. The two are complementary rather than competing, and differ in three ways:
In addition, these works depend on task specific architectures for recommendation or knowledge graph completion, so they cannot be directly compared in our shallow embedding setting. In contrast, SL(n) is a general representation space and has been shown to be effective on several tasks, including reconstruction, link prediction, node classification, and ordered composition. Our ablation study also shows that the full SL(n) clearly outperforms Flat (removing the nonlinear Lie group structure) and Polar (keeping both curvature signs without coupling, see Q5).
Q2(&W2): Controlled Comparison under Matched Parameterization and Optimization:
Thank you for this question. To satisfy their constraints, all manifolds need to choose which parameters enter the optimizer. SL(n) uses Lie algebra coordinates, which are mapped by the exponential map and then optimized by standard AdamW. Therefore, EXP-AdamW is not a special optimizer, but a general parameterization that allows SL(n) to be trained directly with AdamW. On HumanCyc, OGBL-PPA, and Airport, all geometries use strictly matched hyperparameters and dimensions. Since the matrix manifolds were originally matched by matrix dimension, we additionally provide results on KEGG with matched intrinsic dimension:
With matched intrinsic dimension, the conclusion does not change: SL(8) remains the best on all metrics.
Q3(&W2): Computational Cost:
Thank you for this question. We measured all geometries on the same single H200 GPU (3 warm up iterations, then 10 measured iterations with CUDA synchronization). Each iteration includes sampling, forward, backward, gradient clipping, and the optimizer step, with an effective positive edge batch size of 4,194,304.
SL(8) is about 1.3 times slower per update than the strongest vector baseline, and is faster and uses less memory than matrix manifolds (SPD(8) and Siegel(8)). The total training time is 63.18 h versus 45.05 h, which also includes evaluation, communication, and I/O. The higher memory comes from intermediate matrix operations, not from parameter storage. Full results are in the revised appendix (p. [19]).