- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SCOPE (Self-Calibrated Ordered Principal Encoding), a feature-compression framework for tabular foundation models (TFMs) in high-dimensional, low-sample-size (HDLSS) settings. The method first constructs a global feature ordering using LENS, which combines medoid-based nearest-neighbor initialization, candidate-pruned 2-opt refinement, and a budgeted minimum linear arrangement objective. Given this ordering, SCOPE estimates the effective rank of the data to determine the compressed output dimension, partitions the ordered features according to cumulative transition distances, and applies local principal component projections to obtain a compact representation.
Critical strengths
The paper proposes a tuning-free compression framework for HDLSS tabular data, combining feature ordering, spectral complexity estimation, and local PCA projections. This is consequential because it provides a practical way to adapt high-dimensional data to tabular foundation models without dataset-specific tuning or manually chosen output dimensions. The experiments are also reasonably broad, covering multiple datasets and baselines.
Critical weaknesses
- The rationale behind the parameter choices in the LENS module is insufficiently justified. Although the proposed configuration is intended to avoid dataset-specific hyperparameter tuning, it is unclear whether key parameters such as k, b_TSP, b_MinLA, eta, and R are theoretically motivated, empirically selected, or heuristic defaults. Without sensitivity analysis, it is difficult to assess how these choices affect feature ordering, compression quality, and downstream performance, or whether the configuration remains effective across datasets with different characteristics.
- The empirical evidence for SCOPE's effectiveness is not fully convincing. In Table 2, the performance differences between SCOPE and the second-best methods appear marginal, and no statistical significance tests are provided to determine whether the reported improvements are meaningful. In addition, the detailed results in Appendix G show that SCOPE is often outperformed by competing methods or achieves only marginal gains. This raises concerns about the consistency and practical significance of its claimed performance advantages.
- Writing and readability. The paper would benefit from clearer writing and the removal of redundant content, such as the second paragraph of the Introduction. The layouts of Figures 1 and 2 could also be refined to improve visual clarity.
- Reference formatting. The references are inconsistently formatted and should be standardized.
Questions for authors
- Parameter settings in the LENS module. Could the authors clarify the rationale for the parameter settings in the LENS module, including the edge-removal parameter k, b_TSP, b_MinLA, eta, and R? Are these values theoretically derived, empirically selected, or heuristic defaults? How sensitive are the resulting feature orderings, compressed representations, and downstream performance to these parameter choices across datasets with different characteristics?
- Statistical significance of experimental results. Could the authors provide statistical significance tests for the results in Table 2 to determine whether the reported improvements over the second-best methods are statistically meaningful? Given that the detailed results in Appendix G show that SCOPE is frequently outperformed by competing methods or achieves only marginal gains, how do the authors justify the claim that SCOPE provides consistent and practically significant performance advantages?
6 comments
Response to Reviewer WzPg (2/5)
Table C1: LENS ordering quality sensitivity. Dataset-balanced means over 12 FOE-selected benchmarks. Time ratio, TSP cost difference, and MinLA cost difference are computed relative to D within each dataset before averaging; lower ratios/costs are better. Ordering score is normalized independently within each dataset across the same 12 settings (higher is better). Edge overlap denotes adjacency agreement with D where D denotes the default configuration (b_TSP,b_MinLA,η,R)=(30,4,1,20).
| Setting | Score ↑ | Time ratio ↓ | ΔTSP (%) ↓ | ΔMinLA (%) ↓ | Edge overlap ↑ |
|---|---|---|---|---|---|
| D | 0.653 | 1.000 | +0.000 | +0.000 | 1.000 |
| T10 | 0.610 | 0.667 | +0.163 | -0.077 | 0.869 |
| T20 | 0.680 | 0.800 | +0.039 | +0.019 | 0.881 |
| T60 | 0.601 | 1.460 | -0.103 | -0.004 | 0.867 |
| L2 | 0.671 | 0.923 | +0.000 | +0.036 | 0.994 |
| L8 | 0.633 | 1.048 | +0.000 | -0.008 | 0.992 |
| E0 | 0.543 | 0.824 | -0.023 | +0.665 | 0.996 |
| E.5 | 0.674 | 0.963 | -0.012 | +0.011 | 0.993 |
| E2 | 0.637 | 1.029 | +0.023 | -0.078 | 0.994 |
| R0 | 0.531 | 0.724 | -0.023 | +0.691 | 0.995 |
| R10 | 0.681 | 0.909 | +0.000 | +0.021 | 0.999 |
| R40 | 0.640 | 1.048 | +0.000 | +0.000 | 0.999 |
Table C2: SCOPE compression quality sensitivity. Dataset-balanced averages of held-out reconstruction retention (%) across 25 matched folds per dataset. Δ is the alternative minus D in percentage points; |Δ| is its mean absolute value across datasets. The fold-local output budget M* was invariant to all LENS parameter changes (12/12 datasets; 300/300 matched dataset-fold groups).
| Setting | Retention (%) | Δ (pp) | Mean |Δ| (pp) | Mean M* | Invariant M* |
|---|---|---|---|---|---|
| D | 50.41 | +0.000 | 0.000 | 535.6 | 12/12 |
| T10 | 50.12 | -0.285 | 0.449 | 535.6 | 12/12 |
| T20 | 50.48 | +0.066 | 0.307 | 535.6 | 12/12 |
| T60 | 50.49 | +0.082 | 0.206 | 535.6 | 12/12 |
| L2 | 50.27 | -0.135 | 0.145 | 535.6 | 12/12 |
| L8 | 50.37 | -0.041 | 0.215 | 535.6 | 12/12 |
| E0 | 50.37 | -0.037 | 0.092 | 535.6 | 12/12 |
| E.5 | 50.50 | +0.095 | 0.188 | 535.6 | 12/12 |
| E2 | 50.75 | +0.338 | 0.367 | 535.6 | 12/12 |
| R0 | 50.38 | -0.025 | 0.087 | 535.6 | 12/12 |
| R10 | 50.33 | -0.081 | 0.094 | 535.6 | 12/12 |
| R40 | 50.40 | -0.013 | 0.013 | 535.6 | 12/12 |
Table C3: Downstream predictive sensitivity of SCOPE + TabPFN-3. Dataset-balanced mean ROC-AUC (%) over 12 datasets and 25 matched folds per dataset. Δ is the alternative minus default D, in percentage points. Confidence intervals are unadjusted 95% dataset-bootstrap percentile intervals of the mean difference (30,000 resamples). W/T/L (Win/Tie/Loss) uses practical equivalence defined as |Δ_d| ≤ 0.5 pp. Across 11 paired Wilcoxon comparisons, none achieves p < 0.05 after Holm correction.
| Setting | ROC-AUC (%) | Δ (pp) | 95% CI (pp) | W/T/L |
|---|---|---|---|---|
| D | 94.33 | +0.000 | — | 0/12/0 |
| T10 | 94.08 | -0.244 | [-0.57,+0.01] | 0/10/2 |
| T20 | 94.49 | +0.158 | [-0.13,+0.45] | 4/7/1 |
| T60 | 93.92 | -0.403 | [-0.78,-0.05] | 1/7/4 |
| L2 | 94.18 | -0.150 | [-0.54,+0.13] | 1/10/1 |
| L8 | 94.25 | -0.079 | [-0.39,+0.23] | 2/8/2 |
| E0 | 93.99 | -0.339 | [-0.79,+0.01] | 0/9/3 |
| E.5 | 94.19 | -0.138 | [-0.42,+0.12] | 2/8/2 |
| E2 | 94.24 | -0.086 | [-0.41,+0.20] | 1/8/3 |
| R0 | 93.99 | -0.342 | [-0.81,+0.03] | 1/8/3 |
| R10 | 94.25 | -0.075 | [-0.21,+0.03] | 0/11/1 |
| R40 | 94.35 | +0.020 | [-0.01,+0.07] | 0/12/0 |
- See L3498-3509, L3551-L3563, L3603-L3617, L3662-L3667, and Tables L13, L14, L15, L16 in the updated manuscript.
→ Please continue to the next comment.
Response to Reviewer WzPg (3/5)
W2. The empirical evidence ... performance advantages.
Q2. Statistical significance ... performance advantages?
Statistical significance and predictive consistency. Appendix G reports ROC-AUC for downstream classification, which serves as one application for evaluating the predictive utility of SCOPE’s compressed representations. SCOPE’s primary objective is to construct compact, informative representations rather than introduce a new classifier. Its compression results should therefore be assessed jointly through dimensionality reduction, representation quality, and downstream computational savings, with ROC-AUC measuring how well predictive information is retained. To address the reviewer’s concern and further validate SCOPE's predictive effectiveness, we conduct comprehensive statistical significance analyses across all 30 datasets extracting results from Tables 2, G1, G2, G3, G4 using paired Wilcoxon signed-rank tests with Holm correction, Friedman tests, and Nemenyi post-hoc comparisons. The Friedman test confirms statistically significant differences over all 10 comparative compressors (χ²=225.17, p<0.001), with SCOPE achieving the best average rank of 2.20 (Table C4). Importantly, paired Wilcoxon tests with Holm correction establish statistically significant improvements (p_adj<0.05) for SCOPE over all ten compression baselines, including supervised PLS. Specifically, SCOPE outperforms PCA on 22 datasets (W/T/L: 22/4/4; p_adj=0.0019) and NSC-pSP on 21 datasets (21/3/6; p_adj=0.0020), achieving mean ROC-AUC improvements of 1.30 and 1.48 percentage points, respectively. SCOPE also demonstrates strong improvements over nonlinear and manifold-based compressors, achieving 30/0/0 W/T/L against UMAP, ParamRepulsor, PaCMAP, and LocalMAP. Domain-specific analyses further reinforce these findings. On extreme dimensional omics datasets, SCOPE achieves a leading average rank of 1.50 and outperforms PCA on all six datasets (Table C5). Notably, on 12 biological HDLSS datasets, SCOPE achieves the best average rank of 1.83 and statistically significant improvements over all nine unsupervised compression baselines, including PCA (11/0/1; p_adj=0.0293) and NSC-pSP (10/0/2; p_adj=0.0293) (Table C8). On the five text datasets, SCOPE achieves the best average rank of 2.60, outperforming PCA and NSC-pSP on three datasets each, while achieving consistent wins against GRP, UMAP, ParamRepulsor, PaCMAP, and LocalMAP (5/0/0 W/T/L for each; Table C6). On the seven face image datasets, SCOPE maintains highly competitive predictive performance, achieving near-ceiling ROC-AUC with small differences among the leading compression methods. It outperforms UMAP, ParamRepulsor, PaCMAP, and LocalMAP on all seven datasets (7/0/0 W/T/L for each), while remaining closely competitive with PCA and NSC-pSP (Table C7). Statistical comparisons are performed using dataset-level mean ROC-AUC scores, treating each dataset as one paired observation; the domain-specific analyses provide complementary evidence across benchmark categories. Collectively, these findings establish statistically supported cross-dataset improvements for SCOPE over existing compression methods, including supervised PLS, while demonstrating consistent predictive advantages across diverse high-dimensional data domains and particularly strong results in biological HDLSS settings.
Table C4: Cross-dataset statistical comparison of SCOPE.
Pooled comparison across 30 datasets and over 10 compression methods, including supervised PLS, with Raw as an uncompressed reference. W/T/L denotes wins, ties, and losses of SCOPE against each comparator. Δ is the mean ROC-AUC difference in percentage points (SCOPE minus comparator). p_W,H denotes two-sided Wilcoxon signed-rank p-values with Holm correction across ten comparisons; p_N denotes Nemenyi all-pairs p-values. Confidence intervals are unadjusted 95% domain-stratified bootstrap intervals. Raw is excluded from the multiple-comparison correction.
| Comparator | W/T/L | Δ (pp) | 95% CI (pp) | p_W,H | p_N |
|---|---|---|---|---|---|
| PCA | 22/4/4 | +1.30 | [+0.69,+1.95] | 0.0019 | 0.786 |
| NSC-pSP | 21/3/6 | +1.48 | [+0.75,+2.23] | 0.0020 | 0.463 |
| AE | 24/3/3 | +2.31 | [+1.34,+3.44] | 3.64e-5 | 0.370 |
| GRP | 26/2/2 | +2.58 | [+1.95,+3.20] | 5.59e-7 | 0.040 |
| Kernel PCA | 26/3/1 | +2.54 | [+1.89,+3.20] | 4.47e-7 | 0.0074 |
| UMAP | 30/0/0 | +10.29 | [+7.99,+12.97] | 1.86e-8 | 3.28e-11 |
| ParamRepulsor | 30/0/0 | +11.46 | [+8.76,+14.42] | 1.86e-8 | <1e-12 |
| PaCMAP | 30/0/0 | +16.29 | [+13.53,+19.28] | 1.86e-8 | <1e-12 |
| LocalMAP | 30/0/0 | +18.18 | [+15.32,+21.27] | 1.86e-8 | <1e-12 |
| PLS (supervised) | 16/3/11 | +1.44 | [+0.71,+2.21] | 0.028 | 0.786 |
| Raw | 13/3/14 | -0.30 | [-0.68,+0.13] | — | — |
→ Please continue to the next comment.
Response to Reviewer WzPg (1/5)
We thank the reviewer for the constructive feedback and for recognizing the practical significance of our tuning-free compression framework for HDLSS tabular data. We particularly appreciate the positive remarks on its ability to adapt high-dimensional data to tabular foundation models without dataset-specific tuning or manually selected output dimensions, as well as the acknowledgment of our broad experimental evaluation.
LENS parameter settings and theoretical rationale. We emphasize that these parameters are fixed algorithmic search-budget constants rather than hyperparameters selected through validation accuracy, downstream predictive performance, or dataset-specific optimization. The parameters are primarily theoretically derived. Their theoretical properties and computational rationale are established in Appendix B5, particularly in Proposition 3, which demonstrates bounded-search behavior and scale-equivariant refinement. Specifically, k=2 corresponds to the classical 2-opt local-search operation. The candidate budgets b_TSP=30 and b_MinLA=4 reflect the different computational costs of the two refinement stages: TSP 2-opt updates require only a constant number of distance lookups, allowing a broader candidate search, whereas exact MinLA evaluations are more expensive and therefore use a smaller candidate budget. The parameter η=1 permits one median adjacent-edge unit of TSP relaxation while preserving scale equivariance under uniform rescaling of the feature distance matrix. Finally, R=20 bounds the number of accepted MinLA refinements, limiting computational overhead. Thus, the selected configuration (30,4,1,20) represents a deterministic, computationally motivated design rather than a set of empirically optimized predictive hyperparameters. As stated in the manuscript, all values remain fixed across datasets without validation-based selection, preserving the tuning-free property of LENS with respect to downstream predictive performance. To complement this theoretical and computational justification, we additionally investigate parameter sensitivity through empirical ablation experiments below (Tables C1-C3).
Empirical LENS parameter sensitivity. To complement the theoretical characterization of the fixed LENS budgets, we conducted a "one factor at a time" sensitivity analysis over 12 configurations on 12 Feature Ordering Effectiveness (FOE)-characterized datasets (8 biological HDLSS, 2 text, and 2 face image datasets), using matched 5×5 repeated CV (3,600 predictions). The 2-opt neighborhood k=2 remains fixed because changing k changes the search algorithm rather than a numerical budget. Tables C1-C3 report ordering quality, held-out reconstruction retention, and downstream ROC-AUC. The default (b_TSP,b_MinLA,η,R)=(30,4,1,20) achieves 94.33% mean ROC-AUC; 9 of the 11 alternatives have a lower dataset-balanced mean, and 98/132 dataset-alternative pairs (74.2%) differ by at most 0.5 percentage points. Removing MinLA refinement (R=0) increases mean relative MinLA cost by 0.691% and reduces ROC-AUC by 0.342 pp; likewise, setting η=0 increases MinLA cost by 0.665% and reduces ROC-AUC by 0.339 pp. Increasing the TSP candidate budget from 30 to 60 increases mean ordering time by 46.0% and reduces ROC AUC by 0.403 pp, whereas increasing R to 40 adds 4.8% ordering time for only +0.020 pp ROC-AUC. A smaller TSP budget of 20 slightly improves mean ROC-AUC (+0.158 pp). These results demonstrate that the proposed default configuration provides stable and competitive predictive performance while maintaining a favorable balance between ordering quality and computational efficiency across diverse datasets. No alternative yields a statistically significant improvement under paired dataset level Wilcoxon tests with Holm correction (p_adj≥0.74). Furthermore, the analytical compression dimension M* remains unchanged across all parameter configurations and matched folds, demonstrating the stability of SCOPE's self-calibrated representation budget. Collectively, these findings support the robustness of the proposed default configuration, which delivers stable and competitive predictive performance with a favorable ordering quality-computational efficiency trade-off, without downstream performance-based tuning. Here, D denotes the default configuration (b_TSP,b_MinLA,η,R)=(30,4,1,20). T, L, E, and R identify changes to b_TSP, b_MinLA, η, and the maximum number of accepted MinLA refinements, respectively; all other parameters remain at their defaults.
→ Please continue to the next comment.