- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SSAtt, which constructs sample-adaptive lower-dimensional SPD representations through hypernetwork-generated projections and Newton–Schulz orthogonalization. Riemannian attention is applied to both original and compact SPD spaces for EEG decoding.
Critical strengths
- The paper addresses a relevant limitation of full-dimensional covariance representations, particularly redundant and noisy directions in EEG decoding.
- The proposed sample-adaptive SPD projections provide a reasonable approach to learning compact task-dependent representations.
Critical weaknesses
-
The ablation results do not consistently support the central multi-scale motivation. The main contribution emphasizes combining multiple compact SPD spaces to capture complementary information. However, Table 5 shows that a single compact scale achieves the best performance in four of the six evaluation settings. Adding additional scales frequently reduces accuracy, including on BNCI2014001 inter-session and MAMEM-SSVEP-II. The full multi-scale configuration provides noticeable advantages only in selected cross-subject settings. These findings suggest that compact dimensionality reduction, rather than multi-scale aggregation, may be responsible for most of the improvements. The paper does not adequately distinguish these two contributions or provide a principled scale-selection strategy.
-
The sample-adaptive projection mechanism lacks a sufficiently clear and rigorous formulation. Section 3.1 defines the hypernetwork input as , although has previously been defined as an entire sequence of SPD matrices rather than a single matrix. The construction of this trial-level descriptor and its consistency across temporal segments are therefore unclear. Furthermore, Newton–Schulz orthogonalization produces only approximate semi-orthogonality and does not recover rank if the initial projection is rank-deficient. The paper provides no quantitative analysis of orthogonality residuals, conditioning, or the resulting dependence on eigenvalue rectification. These details are important because the preservation of SPD geometry is a central methodological claim.
-
The improvements are not sufficiently isolated from increased representation capacity. SSAtt concatenates representations from the original SPD space and additional compact branches, increasing both feature dimensionality and model complexity. Although Table 4 investigates adaptive projection components, the paper lacks a capacity-matched original-space attention baseline and simpler learned-projection alternatives. Consequently, the results do not establish whether the improvements specifically arise from submanifold-aware geometric attention rather than additional trainable parameters, feature aggregation, or conventional dimensionality reduction.
-
The accuracy improvements are relatively small compared with cross-subject variability and computational overhead. In Table 1, the inter-subject improvements over GyroAtt-SPD are only 1.2 percentage points on both motor-imagery datasets, while the reported standard deviations are approximately 13–16 percentage points. No paired statistical significance analysis is provided to establish the consistency of these improvements across subjects. Furthermore, Table 3 shows increased runtime, reaching 3.01 versus 1.64 seconds per epoch on BCI-ERN. The claimed accuracy–efficiency trade-off therefore requires stronger quantitative justification, particularly given the limited multi-scale benefits observed in Table 5.
Questions for authors
See weekness.
4 comments
3(W3). The Benefits of Submanifold-Aware Geometric Attention
-
Sample-adaptive projections. We reproduce the relevant comparison from Table 4 in Table C below. The “Fixed” setting replaces our sample-adaptive transformation with a conventional learnable BiMap projection. The attention branches, compact dimensions, aggregation structure, and classifier input dimensionality remain the same. SSAtt with sample-adaptive transformations consistently outperforms this alternative across all six settings, supporting the benefit of adapting the compact SPD geometry to the input covariance structure.
-
Aggregation of submanifold-aware attention. As discussed in our response to W1, Table A compares SSAtt with and without scale aggregation at matching compact dimensions. Retaining aggregation improves performance across all six settings, demonstrating the benefit of jointly exploiting original and sample-adaptive compact SPD representations. Together, these ablations support the contributions of sample-adaptive geometric modeling and attention aggregation to SSAtt's performance.
Table C. Comparison of learnable BiMap and sample-adaptive projections, reproduced from Table 4.
| Projection | BNCI2014001 (Inter-session) | BNCI2014001 (Inter-subject) | BNCI2015001 (Inter-session) | BNCI2015001 (Inter-subject) | MAMEM-SSVEP-II | BCI-ERN |
|---|---|---|---|---|---|---|
| Learnable BiMap (“Fixed”) | ||||||
| Sample-adaptive projection |
4(W4). Statistical Significance Analysis and the Choice of Scale Configurations
Table D. Paired -test results comparing SSAtt with GyroAtt. denotes , and denotes .
| Metric | BNCI2014001 (Inter-session) | BNCI2014001 (Inter-subject) | BNCI2015001 (Inter-session) | BNCI2015001 (Inter-subject) | MAMEM-SSVEP-II | BCI-ERN |
|---|---|---|---|---|---|---|
| Gains (pp) | 1.1 | 1.2 | 1.1 | 1.2 | 2.6 | 3.3 |
| Significance |
Table E. Performance and runtime of SSAtt under different compact scale configurations on MAMEM-SSVEP-II and BCI-ERN. The best performance and lowest runtime for each dataset are bolded.
| Scales | Dims. | MAMEM-SSVEP-II Accuracy (%) | MAMEM-SSVEP-II Time (s/epoch) | BCI-ERN AUC (%) | BCI-ERN Time (s/epoch) |
|---|---|---|---|---|---|
| 1 | [4] | 66.91 | 2.68 | 79.37 | 2.43 |
| 2 | [3,4] | 66.84 | 3.37 | 78.10 | 2.65 |
| 3 | [3,4,5] | 67.00 | 3.70 | 77.73 | 3.11 |
| 4 | [3,4,5,6] | 67.55 | 4.06 | 77.68 | 3.51 |
| 5 | [3,4,5,6,7] | 67.00 | 4.65 | 77.68 | 3.92 |
| 6 | [3,4,5,6,7,8] | 67.55 | 5.29 | 78.11 | 4.46 |
| 7 | [3,4,5,6,7,8,9] | 68.27 | 6.04 | 77.89 | 5.04 |
| 8 | [3,4,5,6,7,8,9,10] | 66.73 | 7.05 | 76.51 | 4.96 |
| 9 | [3,4,5,6,7,8,9,10,11] | 66.48 | 8.21 | 76.36 | 5.94 |
We reported the paired -test results in Table D.
We agree that performance gains should be assessed together with computational cost. We added experiments evaluating performance and runtime under different compact scale configurations, as reported in Table E. Each additional scale introduces projection and attention computation, and its benefit depends on the complementary information it provides. Among the tested configurations, MAMEM-SSVEP-II accuracy peaks at seven scales and declines with further expansion as runtime increases. BCI-ERN achieves its highest AUC and lowest runtime with one scale. These results support task-specific scale configurations that balance performance gains and computational cost. We included this analysis in the revised paper.
Thank you for the detailed response and the additional experiments. However, I remain skeptical regarding the primary source of the performance gains. The newly added Table E shows that, on the MAMEM-SSVEP-II dataset, an accuracy of 68.27% is achieved using seven scales; yet, in the original Table 5, an accuracy of 68.8% was already attained using just a single compact scale (with a dimension of 8). Furthermore, on the BCI-ERN dataset, increasing the number of scales often leads to a decline in performance while simultaneously raising computational costs. Consequently, I will maintain my current rating.
Thank you for your prompt response. We examined the source of the gains through two ablations. Removing scale aggregation (Table A) or replacing sample-adaptive transformations with conventional learnable BiMap projections (Table C) reduces performance across all six settings. These results support the contributions of both sample-adaptive projections and representation aggregation.
We would also like to clarify that single-scale SSAtt already aggregates the original SPD representation with one sample-adaptive compact representation. Multi-scale SSAtt adds further compact spaces, improving inter-subject performance from 53.1% to 53.5% on BNCI2014001 and from 76.3% to 77.8% on BNCI2015001.
We agree with your observation that the single-scale [8] configuration outperforms the seven-scale configuration on MAMEM-SSVEP-II, and that additional scales increase cost without improving BCI-ERN performance. These findings support task-dependent use of additional compact scales. We will make this distinction and the comparison scope of Table E explicit in the revised discussion.
We thank Reviewer hYr2 for the careful review and the suggestive comments. Below, we address the comments in detail.
1(W1). Performance Gains beyond Compact Dimensionality Reduction
We added an ablation variant, SSAtt (w/o scales aggregation), by removing scale aggregation from single-scale SSAtt while retaining compact SPD projection and attention. Single-scale SSAtt aggregates the original representation with one sample-adaptive compact representation. As shown in Table A, it outperforms the variant without aggregation across all six settings at matching compact dimensions. These results demonstrate the additional benefits of aggregating original and sample-adaptive compact SPD representations beyond compact dimensionality reduction. We included this ablation study in the revised paper.
Table A. Comparison of SSAtt with and without scale aggregation across six evaluation settings. Dims. denotes compact SPD dimensions. The best result in each setting is bolded.
2(W2). Clarification of Sample-Adaptive Projections and Numerical Stability of Orthogonalization
Table B. Condition number and normalized orthogonality errors of projection matrices before and after eight Newton–Schulz iterations. κ=σmax/σmin and eorth=∥WW⊤−Ik∥F/k. The scales k1,k2,k3 follow the dimension order listed in Dims.
Clarification of sample-adaptive projections. For each temporal segment s, the descriptor is computed from its SPD matrix as us=vech(logXs). The shared hypernetwork generates the corresponding dynamic component ΔWs(m), which is combined with the shared base projection Wb(m). All segments follow the same procedure with shared parameters, while their dynamic components depend on their respective inputs. We added the segment index s to the relevant descriptors and projections in Section 3.1 to clarify this formulation.
Numerical stability of orthogonalization. SPD preservation requires full-row-rank projections. We initialize semi-orthogonal base matrices with zero dynamic components and observed full numerical row rank in the evaluated projections across the six settings. Table B shows that eight Newton–Schulz iterations yield condition number close to 1 and near-zero normalized orthogonality errors across all compact scales, supporting the numerical stability of the sample-adaptive transformations. ReEig additionally floors small eigenvalues after projection as a numerical safeguard.