- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes the feature-space alignment hypothesis, arguing that successful pruning should preserve the effective computation in feature space rather than remain close to the dense model in parameter space.
Critical strengths
The resulting feature-aware masks, especially when combined with OBS-style compensation in FLO, perform well at high sparsity. The SAE experiments are also interesting because they show that much of the oracle benefit can be recovered without direct access to the true embedding.
Critical weaknesses
The core argument relies on a specially constructed setting where the feature-space mapping is explicitly available. It is unclear how directly this notion extends to deep nonlinear networks or modern transformers. The additional experiments on Digits, UCI datasets, and deeper controlled networks are useful, but still relatively far from realistic large-scale models.
The proposed MIP objective is closely related to preserving the layer output on the embedded representation. It would be important to compare against a standard activation- or layer-output reconstruction objective. Such a comparison would clarify whether the gains specifically support the proposed feature-space interpretation, rather than the more general principle of preserving layer function. The MIP formulation is NP-hard and therefore serves mainly as an oracle. In addition, MIP alone is often comparable to OBS in the one-shot setting, while the strongest method is the hybrid FLO, which combines the feature-aware topology with OBS compensation.
Questions for authors
see weakness
4 comments
Following up with new evidence for feature-space alignment hypothesis in Llama 3.2 1B
We would like to follow up with additional results addressing your concern about whether the feature-space perspective extends to modern and larger scale architectures. Since our initial response, we have added experiments on Llama 3.2 1B examining how feature-map preservation relates to pruning performance under magnitude pruning, Wanda [1], and SparseGPT [2], allowing us to investigate this relationship beyond our controlled setting. We show that the feature-space perspective remains informative at the scale of modern language models: better pruning performance accompanies convergence to the dense feature-map representations despite greater divergence in weight space.
We trained TopK SAEs, as we did in Section 4.4, on the dense input activations of the middle MLP layers of Llama 3.2 1B. We then compared pruning the up projection to 50%, 60%, 70%, and 80% sparsity with magnitude pruning, Wanda, and SparseGPT, pruning one layer at a time. Following pruning, we measure the perplexity (lower is better) of the resulting model, as well as the changes in the weights and the feature map , where is the SAE decoder, for each pruning condition. is used only for this post-pruning analysis. We used disjoint text data for SAE training, calibration, and evaluation.
In terms of language modeling performance, SparseGPT achieves the lowest perplexity, followed by Wanda and then magnitude pruning, as expected (Figure 27). Crucially, weight preservation ranks these methods in exactly the opposite order to performance: magnitude pruning preserves the weights most closely to the dense model but yields the highest perplexity, while SparseGPT changes them most and yields the lowest (Figure 10a, b). By comparison, feature-map divergence from the dense model tracks performance across pruning methods: within each examined layer, smaller changes in the feature map consistently accompany lower perplexity (Figure 10c, d). This distinction persists across the tested sparsity levels, with Wanda and SparseGPT consistently changing the weights more than magnitude pruning relative to the dense model, while changing the feature map less (Figure 28).
Across the examined layers and sparsity levels, closer preservation of the feature map consistently accompanies better language modeling performance, even though these methods do not explicitly optimize the SAE-derived map. These findings support the relevance of the feature-space alignment hypothesis to a pretrained transformer and its usefulness for understanding existing pruning methods. We have added these results, including analyses of feature preservation across calibration feature firing rates, to section 4.5 and appendix A.14. We hope this additional evidence helps address your concern about the applicability of our findings beyond our controlled models.
I thank the authors for the detailed response and the addtional experiments, I think those response have solved most of my concerns.
First, the results on Llama 3.2 1B is really valuable, it further support the hypothesis, although the author do not conduct their pruning method on LLM, I view it an open question not the significant shortcome of this paper.
then, the results on layer-output reconstruction and combinatorial OBS help clarify the relationship between the proposed method and preserving the layer output. Figure 8 and the FLO results also solved my previous concerns about MIP and OBS comparison, highlighting the value of the mask.
Overall, I think the author has addressed most of my question and make the paper more strong, thus I am willing to raise the rating by 1.
Thank you!
Thank you for your time and constructive discussion. We greatly appreciate your support of the work and your updated assessment. We feel that your comments have helped improve the work substantially, and agree that the remaining open questions are crucial to explore in future work.
We would like to thank the reviewer for your thoughtful review and for engaging seriously with the paper’s main intuition. We also appreciate how you found our recovery of oracle benefit without the true embedding interesting. We address your concerns below:
Regarding scale, we agree that establishing how broadly this mechanism applies to larger nonlinear networks and transformers remains an important direction for future work. Even in a small model, however, accuracy alone does not reveal whether a sparse model preserves the dense model’s learned feature structure or achieves similar performance by reorganizing its representation. The known DNF clauses let us examine this question directly: much of the codes persist in the same neurons and for the same clauses even after pruning removes 75% of the weights in W1, while their degradation across sparsity levels tracks increasing loss (Figures 2, 3). Explicitly selecting sparse weights to reconstruct the effective map retains more of these codes, even though the optimizer never receives the clause assignments (Figure 7). At this scale, we can inspect how pruning interacts with computation and use MIP to test whether preserving that computation helps maintain accuracy. We have revised the paper to make this scientific motivation and the scope of our conclusions explicit (L53, L57, L63).
Regarding preserving the layer outputs, we agree that the two objectives are closely related. Our objective for Equation 1 was a deliberate experimental choice, as our original motivation concerns distortion of the full effective map, while the layer output reconstruction objective weights the changes in the map according to the effect of observed inputs. We ran this control using the weighted criterion for the feature-based mask selection. In our experiments, weighting often improved one-shot accuracy on the real data benchmarks. After finetuning, the differences largely narrowed, suggesting that both mask selection criteria support similar final accuracies (Figure 21). These results have been added to the appendix. Ultimately, both objectives are consistent with preserving layer function under pruning, a central goal in practical model compression. Our feature-space view further allows us to interpret what this preservation means for the model’s learned feature representation. Thus, our analysis connects functional reconstruction to the structure of the model’s computation. We have clarified this connection in the revision (L293, L439, Section A.12).
Regarding one-shot performance, we agree that MIP and OBS are often comparable before finetuning. We find the hybrid FLO most scientifically interesting, since it combines the two criteria (loss-based and feature-based) at different stages, suggesting that they provide complementary information for pruning. Additionally, Figure 8 helps isolate the contribution of the mask itself, where the MIP mask (with the dense weights) may start at a lower accuracy than the other techniques, yet recover to higher accuracy under the same finetuning budget.
Thank you again for your engagement with our work and for your useful comments. We believe that the clarified connection to layer reconstruction and the additional control experiments strengthen the paper and make its scientific scope clearer.