- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper treats a pretrained ResNet as a set function over binary residual-branch masks and uses Möbius inversion to decompose its logits exactly into individual branch effects and higher-order interactions. It proves an bound for a fixed -way interaction in an idealized smooth residual stack as the residual scale decreases. Exhaustive mask evaluations on ImageNet-pretrained ResNet-18 and ResNet-34 show that squared interaction-coefficient mass peaks at orders 5 and 10, respectively. The authors also study coefficient concentration, reconstruction from selected interactions, and how the selected sets vary across images and classes. They interpret the latter as implicit soft routing despite dense execution.
Critical strengths
-
The residual-mask formulation gives a precise way to separate masked-network responses from additive interaction coefficients. The exhaustive evaluation makes the decomposition and its numerical reconstruction check convincing.
-
The paper distinguishes several quantities that are easily conflated: coefficient mass, logit reconstruction, prediction agreement, and input dependence. Reporting both ResNet-18 and ResNet-34 reveals an important depth-dependent limitation rather than hiding it.
Critical weaknesses
-
The evidence for a sparse functional representation is substantially weaker than the main narrative suggests. Appendix H, Tables 8 and 10 show that retaining 50% of ResNet-34’s interactions captures 97.90% of vector squared-coefficient mass, yet gives relative logit error 13.87 and only 0.60% agreement with the full model’s predictions. Reaching 10% logit error requires 99.495% of the interactions on average. Signed cancellation therefore makes coefficient-mass concentration a poor proxy for a small set of experts carrying the prediction. This directly limits the proposed routing interpretation.
-
The evidence that inputs select meaningfully different routes is modest for the label-free vector readout. At roughly 13% retention, the selected sets have mean Jaccard overlap 0.871 and 0.892 with a global set in ResNet-18 and ResNet-34, while the same-class versus different-class gaps are only 0.0179 and 0.0137 (Appendix I, Tables 11–12). The stronger scalar results select a potentially different predicted-class logit for each image, so they do not independently establish class-dependent routing over a common readout. The results support small, structured variation around a shared core; the paper should calibrate its central claim to that effect size.
Questions for authors
-
What quantitative criterion makes the observed representation “sparse routing” when ResNet-34 needs almost its entire interaction dictionary for faithful logit reconstruction? Would a cancellation-aware selection method yield substantially better reconstruction at a small retained fraction?
-
How much class-dependent variation remains after accounting for the shared global interaction set and, for the scalar analysis, the choice of predicted-class coordinate? An evaluation on a common readout across images would materially clarify the routing claim.
10 comments
Rebuttal for [W1&Q1] by Authors 【Part 2】
2. Cancellation explains why individual coefficient size is a poor guide to reconstruction
Analysis. Reconstruction error depends on the sum of omitted terms, not just their individual sizes. Writing and for the omitted interactions, we have, under any fixed ordering of the interaction indices,
Magnitude ranking uses individual norms but ignores the cross terms. It can retain a large term while omitting the terms needed to cancel it, worsening reconstruction as the budget increases. Forward selection accounts for the terms already retained through the joint error. This explains why Table 1 gives very different outcomes at the same support size, and why magnitude error need not decrease monotonically.
3. Prediction agreement and 10%-error logit reconstruction are different criteria
We quantify prediction-level sparsity by the retained dictionary fraction at a stated prediction agreement, while reporting logit error alongside it. The new result is 128 of 65,535 terms, 86.45% agreement and 0.2977 relative error. The original 99.495% retention figure concerns reaching 10% relative logit error under magnitude ranking. These are different selection procedures and fidelity criteria; we do not present the new result as achieving that 10% threshold. Nor does an arbitrary interaction support specify an executable branch subset.
Conclusion. The proposed cancellation-aware test finds small supports that preserve most predictions using unchanged original coefficients. It establishes prediction-level sparsity on this cohort while keeping logit fidelity and sparse execution separate.
Manuscript changes:
- Main text:
Abstract (p. 1);Introduction, Section 1 (pp. 1–2);cancellation-aware reconstruction, Section 4 and manuscript Table 2 (pp. 7–8; table on p. 7). - Definitions and explanation:
Section 2.1 (pp. 2–3);cancellation identity and prediction criterion, Appendix K.2 (pp. 48–49). - Experimental details:
Appendix L.2 (pp. 52–53);reconstruction results, Appendix L.3.2 (pp. 53–56), with the primary 2,000-image comparison in manuscript Table 24 and the separate 200-image diagnostics in Tables 25–26 (all p. 55).
Rebuttal for [W2&Q2] by Authors 【Part 1】
[W2/Q2] Class structure under common readouts and beyond the shared core
Response. Class-dependent variation remains under a common readout and after excluding the shared core. We added three tests to distinguish this variation from the two factors raised by the reviewer:
-
Removing the shared core leaves measurable class structure in both models. With the same full-logit readout for every input, the remaining interaction sets have same-class minus different-class Jaccard gaps of 0.032887 for ResNet-18 and 0.036207 for ResNet-34. Both have Bonferroni-adjusted under the four-test primary family (Table 2). Thus, global reuse does not explain all class-dependent variation.
-
The class signal persists without choosing an input's predicted-class coordinate. Every image uses the same four-coordinate vector to rank interactions. After core exclusion, the gaps remain positive: 0.034914 for ResNet-18 and 0.023951 for ResNet-34 (Table 3). These are exploratory checks, reported separately from the primary tests.
-
The same sparse supports that preserve predictions also show class structure. The saved ResNet-34 supports with preserve 86.45% of predictions and have a Jaccard class gap of 0.002532, with Holm-adjusted (Table 4). Labels do not enter support selection. This post-hoc test connects prediction preservation and class structure to the same supports; it is separate from the core-exclusion experiments.
1. Removing the shared core leaves positive class gaps under a common full-logit readout
Experimental setup. We fit the global interaction ranking on 5,000 calibration images and evaluate on a separate fixed cohort of 640 images from 128 classes, five per class. The ranking uses mean normalized squared vector-coefficient energy and does not use labels. At approximately 13% total retention, we fix a core occupying 75% of that budget: for ResNet-18 and for ResNet-34. For each evaluation image, we exclude these global indices before selecting the remaining tail.
Every image uses the same full-logit readout. We measure the mean same-class minus different-class Jaccard similarity of the tail indices. Class controls use 10,000 sampled pairs of each kind, 200 class-block bootstrap repeats, and 100 label shuffles with supports fixed. The prespecified primary family contains four tests: outside-core vector Jaccard and cosine gaps for each model, with a four-test Bonferroni correction.
Table 2: Class structure outside the calibration-fixed global core. Results use the same 640 evaluation images and the complete vector readout. Intervals are marginal class-block bootstrap 95% intervals; the last column gives the one-sided permutation after correction over the four primary tests.
| Model | Outside-core vector Jaccard gap | Class-block 95% CI | Primary-family adjusted |
|---|---|---|---|
| ResNet-18 | 0.032887 | [0.019679, 0.045522] | 0.03960 |
| ResNet-34 | 0.036207 | [0.029767, 0.042473] | 0.03960 |
Results and analysis. Table 2 shows that same-class inputs share more of their remaining interaction indices than different-class inputs in both models. The gaps remain positive after core exclusion and pass the stated four-test correction, while every input uses the identical full-logit readout. The shared global core therefore does not account for all class structure. This detects structured variation around shared computation, not disjoint class-specific routes.
Rebuttal for [W1&Q1] by Authors 【Part 1】
We thank the reviewer for recognizing the precise residual-mask formulation, the exhaustive evaluation, and our distinction between coefficient mass, reconstruction error, prediction agreement, and input dependence. Below, we address your questions about cancellation-aware selection and class structure under a common readout. We have added experiments for both and revised the claims to distinguish prediction-level sparsity from sparse execution.
[W1/Q1] Prediction-level sparsity under cancellation-aware selection
Response. We tested the reviewer's proposed cancellation-aware selection. The results show that small sets of original interaction terms can preserve most predictions, even when magnitude ranking fails. Three points clarify the result and its scope:
Just 128 original terms preserve 86.45% of ResNet-34 predictions. On 2,000 images spanning all 1,000 ImageNet classes, these terms constitute 0.1953% of the dictionary. At this same budget, prediction agreement is 86.45% for forward selection versus 0.30% for magnitude ranking (Table 1). Selected coefficients retain their original values and unit weights.
Joint selection accounts for cancellation that magnitude ranking ignores. Forward selection chooses each added term by its reduction in the combined reconstruction error, accounting for the terms already retained. It changes which original terms are selected, without refitting or rescaling their coefficients.
Our sparsity claim concerns prediction preservation at a reported logit error. We report the retained fraction together with prediction agreement and relative logit error: 0.1953%, 86.45%, and 0.2977, respectively. This does not meet the separate 10%-logit-error criterion. The selection uses the full output and decomposition, so it is an offline test of the representation, not an online router.
1. Retaining 0.1953% of the dictionary preserves 86.45% of predictions
Experimental setup. We use frozen ImageNet-pretrained ResNet-34 at λ=1 on a fixed cohort of 2,000 ImageNet-1K validation images, two per class. A seeded hash of sample IDs fixes this cohort before analysis, independently of logits and outcomes. All images use the complete 1,000-dimensional logit vector as the common readout. For each input, magnitude ranking and greedy forward selection choose K=32 or K=128 terms from the same 65,535 nonempty interactions. Forward selection adds the term that most reduces the current reconstruction error, accounting for the terms already selected.
Both methods include the shortcut-only baseline and retain every selected original vector coefficient at weight one. We do not refit or rescale coefficients, and true labels do not enter support selection. Relative logit error is max(∥hx(1[L])∥2,10−12)∥hx−hx(1[L])∥2; prediction agreement compares the reconstructed and full-model argmax. Forward selection uses the full-model target and the complete decomposition, so it is an offline diagnostic, not an online router.
Table 1: Magnitude-based and cancellation-aware reconstruction in ResNet-34. Both methods use the same 2,000 images, common vector readout, original coefficients, and support cardinality. Agreement is with the full-model prediction, not ground-truth accuracy.
Results and analysis. Table 1 shows that forward selection preserves 74.40% of predictions at K=32 (class-block bootstrap 95% CI [72.30%, 76.35%]), with relative error 0.4629 [0.4612, 0.4646]. At K=128, agreement reaches 86.45% [85.00%, 88.10%], while relative error falls to 0.2977 [0.2964, 0.2992]. Ground-truth accuracy is 73.40% for the full model, 64.00% at K=32, and 70.10% at K=128.