- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
CKA is a measure for the similarity of representations, e.g., those learned by different neural networks or those between different layers of a single network. The central hypothesis of the paper is that CKA is obscured by the grouping of inputs into different labeled classes. The paper proposes to decompose the similarities into within and between class similarities and correspondingly decompose the calculation of CKA into these two components. The results demonstrate that the between class variation may have a significant impact on the calculated CKA measure.
Critical strengths
The paper presents novel insights that help understand the properties of CKA, which is a widely used method for investigating representation similarities.
Critical weaknesses
The novelty is somewhat limited by the fact that Cui et al. (2022) already demonstrated that the population structure of the dataset confounds CKA computation. In the light of that, the main claim of the present paper, that the population structure caused by class labels affects the calculation of CKA, seems somewhat incremental. The paper would benefit from including some convincing examples where the method makes a concrete, interpretable difference on the results not achievable with previous methods.
For a paper whose topic is similarities of representations between images, it is a clear minus that the paper itself does not include any illustrative visualizations. The writing could also be clearer (starting with the title and the abstract).
Questions for authors
Suggestion: the general audience would likely benefit from introducing the background of CKA, which now comes in Section 3, already earlier.
Suggestion: it would be good to include some illustrative visualizations.
Suggestion: a more in-depth analysis of some real-world examples, ideally from multiple domains (image, text, ...), and a comparison with the closest alternatives, would have been useful.
5 comments
We are following up on our response of November 7, about ten days ago, and thank you again for the review and its concrete suggestions. We have not heard back, and before the discussion closes we would like to know whether the comparison with deconfounded CKA, the new Figure 1, and the text experiments are what you had in mind. If something is still missing, please tell us. The main points follow.
The idea of the paper is easiest to see in Figure 1(a) of the revised PDF. Two toy networks place four classes identically and order the inputs around each class mean in unrelated ways. Their CKA is 0.89. After each class mean is subtracted, which defines within-class CKA (), the value is 0. A CKA value on a labeled dataset thus mixes two agreements, whether two networks place the classes alike and whether they arrange the individual inputs around the class means alike. The paper proves how the two combine and measures each on real networks.
W1. Relation to Cui et al. (2022)
Cui et al. regress an input-similarity matrix out of each representation (dCKA). We applied dCKA to our features with two confounders, pixel similarity and the same-class indicator. With the pixel confounder dCKA stays within 0.025 of ordinary CKA, and with either confounder it keeps the layer correspondence of ordinary CKA (23 of 24 and 24 of 24 combinations of model pair and dataset, Appendix A.18). The class effect remains even when the labels themselves are supplied, because the two adjustments differ in form. dCKA fits one coefficient per similarity matrix, which with the label confounder encodes only whether two inputs share a class. removes every class mean, and with them the whole arrangement of the classes, including which classes lie near which.
Results that CKA and dCKA do not give
- Which models are most alike. At the final layer on ImageNet-1K, ordinary CKA ranks ResNet-18 and DINO ViT-S as the most similar of the six model pairs (0.417, ahead of ConvNeXt-Tiny and EfficientNet-B0 at 0.366), and dCKA keeps this order. That pair also has the largest gap between CKA and . Once class means are removed, the two convolutional networks rank first (0.344 against 0.206).
- Which layers correspond. For ResNet-18 versus ConvNeXt-Tiny, ordinary CKA and both dCKA variants report depths (2,1) as the most similar pair of layers, and reports (1,1). When the two networks are joined at these layers through a small trained layer (model stitching), the choice of keeps 0.967 of the target accuracy against 0.868. The most similar pair changes for four of six model pairs, in 98% to 100% of 1000 resamples of the classes. The bias-corrected per-class average of Kornblith et al. (2019) agrees with on three of the four, and stitching favors the within-class choice for the two convolutional pairs and the ordinary choice for the two pairs with the ViT.
- Where the class effect comes from. Swapping the class means among the classes in one network, with each image kept at the same position relative to its class mean, lowers CKA by 45% to 85% in all 24 combinations and leaves unchanged. The effect therefore comes from the two networks agreeing on class placement, which neither CKA nor dCKA can test.
- No evaluation labels needed. Clusters computed from a third network give a gap between CKA and as large as the labels do (0.19 to 0.25 against 0.17 to 0.20 on CIFAR-100), clusters of pixels give at most 0.069, and random groups give 0.000.
W2 and suggestions
The revised PDF adds Figure 1 on page 2, which shows the toy case above, the construction in which CKA rises to 0.969 while stays at 0, and the swap on real features for all four datasets. The definition of CKA now appears in the first paragraph of the introduction, and the abstract opens with the two agreements. We kept the title as submitted for the discussion period and would gladly adopt a plainer one. For a second domain we added four text encoders (BERT, RoBERTa, MiniLM, MPNet) on three text classification datasets. The gap is +0.096 to +0.157 on AG-News and +0.220 to +0.301 on DBpedia-14, and the most similar pair of layers changes for 5 of 18 encoder pairs.
We hope this addresses your concerns and suggestions.
Thank you for your rebuttal! I have read it and we will discuss with the other reviewers. The new experiments show that the method produces results different from other methods but I don't see it demonstrated clearly that the changes are for the better. Also, the illustration presented in Figure 1 is perhaps too simplistic to be very helpful. For now, I keep my original score.
We sincerely thank Reviewer Z5Hz for the expert review, for recognizing that the paper offers novel insight into a widely used measure, and for concrete suggestions on comparisons, domains, and presentation. We followed every suggestion with new experiments on the same features.
W1. Relation to Cui et al. (2022), and differences no previous method gives
Cui et al. regress the representation similarity matrix on an input-space similarity matrix. We ran their dCKA on our features with two confounders, the 32x32 pixel similarity and the same-class indicator, on stratified 5,000-image subsets that reproduce the full-set best depth pairs of CKA and CKAw (Appendix A.18, Tables 16 and 17). Best-matching depth pair of the 4x4 grid:
Suggestion. Multiple domains
Four text encoders (BERT, RoBERTa, MiniLM, MPNet), mean-pooled tokens at four relative depths, up to 1000 test examples per class, final layer (Appendix A.17, Table 15).
The effect transfers to text, including changes of the best depth pair. 20-Newsgroups adds an instructive case. Δ is near zero although the class means agree closely, which is the situation of Proposition 3 and is visible only through the decomposition.
W2 and suggestions. Visualization and clarity
Thank you for this suggestion. The revised PDF adds Figure 1 on page 2. Panel (a) shows two toy networks that place four classes identically and arrange the inputs inside each class in unrelated orders, giving CKA = 0.89 and CKAw = 0. Panel (b) scales the shared class component of Proposition 2, driving CKA to 0.969 while CKAw stays 0. Panel (c) shows the one-sided shuffle on real features for all four datasets, where CKA falls while CKAw stays fixed. The CKA definition now appears in the first paragraph of the introduction, the abstract opens with the two agreements CKA mixes, and all figures were redrawn with larger text.
We hope these results address your concerns, and we would be glad to provide any further analysis during the discussion.