- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
There are two branches of study: neural scaling laws and neural redundancy. This paper proposed a method to measure the functional redundancy of attention heads by silencing certain heads and measuring the performance change. They can also measure how much other heads can compensate for the silenced head. Across model families, larger models tend to have more diverse heads but also increasing redundancy, potentially explaining the diminishing returns of scaling laws. Based on the new metric, the paper can also prune the model better by removing the redundant heads, reaching better performance than pruning based on importance-based metrics.
Critical strengths
- The metric is creative and intuitively reasonable. Empirical results support the direction of the claims. I think such a metric can be potentially useful.
Critical weaknesses
- In the paper, the actual analysis focused on the redundancy of attention heads. A similar idea may be easily generalized to MoE. But it is hard for me to imagine how to generalize it to other modules like MLP. The method is therefore too specific and has a limited scope.
- Scientifically, although it is appealing to connect increasing redundancy to diminishing returns of scaling laws, the paper does not provide quantitative evidence for this connection, like predicting scaling laws from redundancy or vise versa. The connection between redundancy and scaling laws is not convincing. And defining redundancy only helps to describe what we have, but not to predict what changes can reduce the redundancy.
- Beyond scientific contribution, the practical usage of the metric also feels limited.
In general, the metric is interesting, but the current paper's limitations make it hard for me to recommend it for acceptance now.
Questions for authors
- Line 146, when first introducing the output discrepancy, , please provide more details. No idea what this function is.
- By reducing the redundancy, can we improve the coefficients or exponents of the scaling laws? What is the theoretical connection between redundancy and scaling laws?
- Based on your results, can you provide an explanation of why redundancy arises? Can you predict what kind of changes (e.g., architectures, optimizers) can reduce the redundancy?
4 comments
Follow-up: Revised manuscript and additional evidence
We thank the reviewer again for the thoughtful comments. We have completed a revised manuscript with substantive main-text additions marked in blue. To facilitate reassessment, we summarize the new evidence and its implications for the three main concerns.
1. Generality beyond attention heads
We applied the unchanged CFS protocol to grouped MLP neurons in ViT-B (Appendix C.4, Table 10):
| Layer | MLP groups | Raw Oracle | 95% CI |
|---|---|---|---|
| 6 | 8 | 0.6120 | [0.5769, 0.6496] |
| 6 | 16 | 0.6856 | [0.6551, 0.7153] |
| 11 | 8 | 0.5221 | [0.4907, 0.5548] |
| 11 | 16 | 0.5813 | [0.5484, 0.6119] |
MLP substitution also exhibits input dependence (cross-input SD 0.232–0.283) and directionality (mean gap 0.146–0.186), including under alternative groupings. This directly demonstrates applicability beyond attention heads, addressing the specific concern about MLP modules.
2. Quantitative links to scaling efficiency
Our controlled GPT-2 experiments compare two scaling paths from the identical W768/D12 baseline (Table 4):
| Scaling path | Added params | Δ Raw Oracle | Loss reduction |
|---|---|---|---|
| Width → W1152 | 125.92M | +0.0397 | 0.1752 |
| Depth → D18 | 42.53M | +0.0029 | 0.0728 |
Depth scaling produces much less growth in substitutability and approximately 23% greater validation-loss reduction per added parameter.
At a fixed parameter count of 124.44M, the head-decomposition experiment provides a complementary comparison (Table 5):
| Heads | Raw Oracle | Rank/H | Validation loss ↓ |
|---|---|---|---|
| 6×128 | 0.2012 | 0.9507 | 3.5707 |
| 12×64 | 0.2125 | 0.9335 | 3.5752 |
| 24×32 | 0.2583 | 0.8725 | 3.5780 |
These controlled results quantitatively relate functional organization to parameter efficiency and performance at fixed capacity. Additional Matched-N and fixed-K Cover/Rank controls (Figure 2; Appendix Figure 7) further show that the natural-family trends persist after controlling for candidate count and graph size.
Predicting scaling-law exponents and improving scaling curves through direct interventions remain long-term goals. The current measurements and controlled findings provide an empirical foundation and testable directions toward them.
3. Redundancy formation and design implications
Training dynamics (§5.4; Appendix A) reveal evolving, non-monotonic substitution structure with different stabilization rates across layers. The width/depth and head-granularity results above also identify concrete architectural variables that change functional organization. These observations motivate causal tests of capacity allocation and CFS-aware regularization, rather than merely describing redundancy in a fixed model.
4. Practical utility
CFS-guided routing reduces ViT-B dense-output KL by 43.5–49.2% relative to Taylor under equal logical head budgets (Table 7). We further extended routing to GPT-2 layers 8 and 11, comparing CFS R2 against Taylor and parameter-matched learned gating (825,091 vs. 822,460 trainable parameters).
The mean dense-output KL results (lower is better) are:
| Layer | Keep K | Taylor | Learned Gating | CFS R2 |
|---|---|---|---|---|
| 11 | 3 | 0.06268 | 0.03116 | 0.02910 |
| 11 | 6 | 0.02691 | 0.01733 | 0.01624 |
| 11 | 9 | 0.01200 | 0.00910 | 0.00732 |
| 8 | 3 | 0.04073 | 0.02883 | 0.04412 |
| 8 | 6 | 0.02408 | 0.01984 | 0.01580 |
| 8 | 9 | 0.01140 | 0.01115 | 0.00463 |
CFS R2 achieves lower mean KL than learned gating in five of six settings, with a maximum reduction of 58.4% (layer 8, K=9). The layer-8, K=3 exception is reported and discussed in §6.2. These results demonstrate functional preservation across vision and autoregressive language models under logical head budgets; realized wall-clock acceleration requires a sparsity-aware backend.
We also explicitly defined in §3.2.
Reply to author rebuttal
I thank the authors for their detailed responses with new experiments.
I wrote 3 weaknesses: the first is about the generality of the proposed metric, the second is about scientific understanding, and the third is about the practical usage of the metric. The response addressed the first weakness very well and the third point acceptably. But the second weakness remains, and I do not think it can be addressed easily.
The current paper remains largely empirical. Although the proposed metric has some theoretical heuristics, the rest of the paper tries to show empirical relations to a range of other performance metrics, supporting the heuristics but without theoretical analysis or further understanding. This is also why I chose "Informativeness: 1: I learned little or nothing new from this paper."
Based on my standard, if a paper is for better understanding, certain theoretical analysis or direct connections between things is needed beyond heuristic connections and empirical correlation or trends.
Therefore, I tend to keep my original score now. But I am still open to increasing my score after more careful reading and thinking.
We thank the reviewer for the further clarification. We understand that the central remaining concern is whether CFS can provide more direct theoretical analysis and further understanding of functional organization beyond empirical trends. To address this point, we conducted additional theoretical derivations and real-model analyses, leading to the following results.
-
CFS admits a clear local geometric structure. Under the local Fisher geometry of the predictive distribution, we show that the quadratic form of CFS can be expressed as constrained projection recovery between component functional directions. This yields a rigorous functional-packing lower bound in a finite-dimensional functional space: when the task-relevant local effects of (H) components lie in a (d)-dimensional space with (H>d), they cannot all be mutually orthogonal, implying unavoidable functional overlap. We further derive the effect of the finite (\alpha)-grid on this limit and obtain an attainable exact minimum Raw Local Oracle value of 0.24 for (H=3,d=2) under the original 16-point (\alpha)-grid.
-
Full CFS captures more than local similarity. We further prove that two models can have exactly the same dense prediction, deletion loss, and Fisher Gram, while their Raw Oracle CFS under full intervention can take different values spanning from 0 to 1. Thus, Full CFS cannot be reduced to representation similarity, effective rank, or local Fisher geometry; it additionally captures conditional functional interactions and compensatory structure under finite interventions.
-
This theoretical distinction explains the source of CFS growth in real scaling experiments. In controlled BERT width scaling, Full CFS increases by 0.07657 from B1 to B3, while the Local component increases by 0.08063. For ViT Small→Large, Full CFS increases by 0.18963, of which 0.14972 is contributed by the Local component. Therefore, in these two independent model families, the observed growth of CFS with scale is primarily associated with increasing overlap among task-relevant local functional directions, rather than merely being an empirical statistic that co-varies with model size.
Together, these results provide a theoretical account of CFS spanning local functional geometry, functional-packing limits, and full conditional intervention structure, and further clarify the source of the functional-organization changes observed during scaling.
If the paper is accepted, we will incorporate the full derivations, proofs, and corresponding experimental results into the camera-ready version. We sincerely thank the reviewer again for raising this important concern, which motivated us to further clarify and deepen the theoretical interpretation of CFS. We hope that these additional analyses address the main concern regarding theoretical analysis and further understanding; if so, we would be very grateful if the reviewer could reconsider the current score. Thank you again for your time and careful evaluation.
We thank the reviewer for recognizing CFS's novelty and potential. We address the concerns about generality, scaling laws, and practical utility with new experiments and clarifications.
1. Beyond attention heads
CFS applies to intervenable components with measurable downstream effects; attention heads offer a convenient additive decomposition, but are not essential.
We additionally applied the same protocol to grouped MLP neurons in ViT-B (layers 6/11; 8/16 groups; 64 inputs; Appendix C.4, Table 10). Raw Oracle is 0.6120/0.6856 and 0.5221/0.5813, respectively. These groups also exhibit input-dependent substitution (cross-input SD 0.232–0.283) and directionality (mean directional gap 0.146–0.186). These properties persist under alternative groupings, although recovery magnitude varies with grouping. This empirically extends CFS beyond attention heads.
2. Functional redundancy and scaling laws
As outlined in Discussion, predicting scaling-law coefficients or exponents and ultimately improving scaling curves by shaping functional organization are long-term research goals. This work takes an important step toward them by directly measuring functional substitutability and quantitatively examining its relationship with model capacity and parameter efficiency.
In controlled GPT-2 scaling (Table 4), starting from the same W768/D12 baseline, widening to W1152 increases Raw Oracle by 0.0397, while deepening to D18 increases it by only 0.0029. Consistent with this difference, depth scaling achieves approximately 23% greater validation-loss reduction per added parameter.
At identical parameter count (124.44M; Table 5), changing head decomposition from 6×128 to 24×32 raises Raw Oracle from 0.2012 to 0.2583, reduces normalized effective functional rank from 0.9507 to 0.8725, and increases validation loss from 3.5707 to 3.5780.
New Matched-N and fixed-K Cover/Rank experiments (Figure 2; Appendix Figure 7) further show that the natural-family functional-organization trends persist after controlling for candidate count and graph size.
These controlled results provide quantitative empirical evidence relating functional substitutability to parameter efficiency, though they do not yet establish a causal prediction of scaling-law exponents. Deriving such predictions and testing whether directly modifying functional redundancy can improve scaling curves remain central goals of our future work. The proposed measure, observed structural regularities, and controlled experiments provide an empirical foundation and concrete, testable directions toward these goals.
3. Why redundancy arises and what could reduce it
Training dynamics (§5.4; Appendix A) show that substitution relations form and reorganize during optimization, following non-monotonic trajectories with different stabilization rates across layers. Changes in substitutability are not always synchronized with performance improvements. Thus, functional redundancy is part of an evolving computational organization rather than merely a static post-training property.
Our controlled experiments further reveal two design-relevant patterns: (i) from a shared baseline, width scaling produces greater growth in substitutability and lower improvement per added parameter than depth scaling; (ii) at fixed parameter count, fewer, wider heads exhibit lower Raw Oracle, higher normalized functional rank, and better validation loss.
These observations suggest that architecture and capacity allocation affect the emergence of independent and substitutable functions. While they do not establish a unique causal mechanism or optimizer-level explanation, they motivate concrete tests, including changing capacity allocation and introducing CFS-aware regularization under fixed architecture and parameter budgets, to examine whether functional organization can be deliberately improved.
4. Practical utility and clarification of D
A lightweight router predicts CFS from forward features, requiring no oracle interventions, labels, or gradients at inference. On ViT-B, CFS routing reduces dense-output KL by 43.5–49.2% relative to Taylor under equal logical head budgets (Table 7). On GPT-2 layers 8/11, CFS R2 achieves lower mean KL than a similarly sized learned gating baseline in five of six settings, with reductions up to 58.4% (Table 8; Appendix F.5). These demonstrate improved functional preservation under logical budgets; wall-clock acceleration requires a sparsity-aware backend.
For Q1, §3.2 now explicitly defines D(y,y~)=DKL(py∥py~): the KL divergence between dense and intervened predictive distributions, over classes or next-token probabilities as appropriate.
We thank the reviewer again for the thoughtful questions. We hope the additional evidence clarifies CFS's scientific contribution and practical value, and welcome further discussion.