- Rating
- 1
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper aims to relax six of the common strong assumptions of causal representation learning methods. Weaker assumptions imply weaker results and instead of disentangling each generative factors individually, they disentangle a subset of generative factors in one unique block. They prove that under certain assumptions that the minimization of their loss imply block-disentanglement. Finally they use their method on a moving robotic arm environment.
Critical strengths
The author suggest a new set of assumptions and its corresponding identifiability theorem
Critical weaknesses
The experiments are clearly not enough to assess if the method achieve disentanglement. The classical disentanglement method seems unrelated to the purpose of the paper and don't seem to have a pertinent baseline. The block-disentanglement benchmark do not have any baseline, rely on one seed of one experiments where there is nothing to disentangle and the metric do not measure the correct property.
Questions for authors
- Is your "block disentanglement" related to "partial disentangled" of [3] ?
- You state in your conclusion that "individual variables cannot be recovered separately", is it theoratically grounded ?
- Graphics in Appendix 6 are hard to read
- What is the purpose of the scale loss ?
Concerning experiments:
- The classical disentanglement method seems to be the one introduced by [1] and relies on the assumption that you aim to relax. What is your contribution for this method and how is it related to the purpose of the paper ?
- The classical disentanglement experiments have for only baseline a partially supervised method, why not use unsupervised method ? It seems hard to compare RoboPEPP and your method
- Why the benchmark of block-disentanglement do not have any baseline ? The metric is highly dependant on the regressor used, therefore it seems impossible to analyze your results without any baseline. You could use other block/partial disentanglement method or you could use classical disentanglement method and aggregate their representation such as done for the baseline in [4] ?
- Additionnaly, the metric only measure one-way regression and not a bijection: if encode all the information , then despite not being block-disentangled. You should use as in [2]
- In the experiments described in Appendix C, what is the unactive block to disentangle from ? It looks like meaning that there is nothing to disentangle, in such case, why not just learn an auto-encoder in latent dimension ?
- You assess that you empiracally relax assumption C6 (known ), however you use in your block-disentanglement experiment with known, how is it different to know ?
- Additionally you explain that you relax assumption C1 (atomic intervention) while you use "one nominally targeted joint per environment", how is it really different thant atomic intervention ?
[1] Linear causal representation learning from unknown multi-node interventions (Varici et al, Neurips 2024)
[2] Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement (Ross et al, ICML 2021)
[3] Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse
Actions, Interventions and Sparse Temporal Dependencies (Lachapelle et al, JMLR 2026)
[4] CITRIS: Causal Identifiability from Temporal Intervened Sequences (Lippe et al, ICML 2022)
3 comments
Rebuttal (part 2 of 2)
Q10. Unknown latent dimension
Our learning objective requires a selected block size and a bottleneck dimension , but does not need us to set . The new experiments demonstrate that its use is not restricted to (which implies known ).
Q11. Atomic interventions
While our main results use single-dominant-joint interventions, we had also conducted experiments under multiple-dominant-joint targets in Appendix C.4.3. Furthermore, even our single dominant joint experiments do not correspond formally to the atomic interventional setting of prior work: (i) there are off-target effects on all other joint angles, and (ii) the observational–interventional contrast is formed by contrasting two halves of videos, rather than collecting independent samples from a priori fixed distributions. Therefore, the embodied setting is significantly different from the usual atomic intervention definitions.
Q1: If your method is a specific case of partial identification, you should explain why more precisely and it would be an important baseline in your experiments
Q5: I don't understand to what extend the study of the classical disentanglement of Varici et al. allows a deeper understanding of your method. What are the conclusions of the classical disentanglement benchmark regarding your method as there is no common metric ? If you do not contribute to this method, the following sentence in Section 5 is highly confusing "we compare the performance of our approach" ?
Q6: I can understand that such comparison could be useful, however you should use at least one of the many classical disentanglement method for a cleaner benchmark. But first you should address the concern raised Question 5 on the purpose of this benchmark relatively to your method
Q7: This is an interesting ablation of , however without a baseline those results cannot be interpreted, we cannot know if your method performs well for or sub-performs for
Q9/Q10: My question is the following: when , why use your method rather than an auto-encoder with ? Concerning results in C.4.4, reverse seems extremely low for the 3 Dataset. But as said earlier, it is hard to draw conclusion without baseline.
Q11: Your main setting is indeed different from the atomic intervention setting, however it feels pretty close to it. Concerning the results in Appendix C.4.3, the Figure 6 uses cryptic notations that I cannot understand
Rebuttal (part 1 of 2)
Q1. Relationship to partial disentanglement
Our definition is a particular partial identification target: only the intervention-affected group ZI must be recovered, and its coordinates may be mixed by an arbitrary diffeomorphism within that group.
Q2. Whether individual variables cannot be recovered
What we mean specifically is that our results apply in settings where the assumptions used for existing elementwise-identification guarantees need not hold. We do not prove that individual variables are impossible to recover separately in every such setting, and we have adjusted the language to make the distinction clear.
Q3. Appendix figures
In our camera-ready version, we will enlarge the axes, legends, and labels in Appendix C to improve readability at normal zoom levels.
Q4. Purpose of the scale loss
Without a scale constraint, the regularizer has a simple degeneracy: If the encoder output is rescaled as h′(x)=ah(x) and the decoder is adjusted to preserve reconstruction, its transformed score differences scale as a−1. Increasing a can therefore reduce the score penalty without improving disentanglement. The scale term in Eq. (10) constrains the mean norm of the encoder output and discourages this trivial rescaling.
Q5. Contribution beyond classical disentanglement
We do not claim the classical disentanglement method of Varıcı et al. (2025) as a new theoretical contribution. We use it as a reference setting to investigate the behavior of theoretically motivated CRL objectives in our experimental framework. Our novel contributions are instead (i) the block-identification result under the relaxed intervention conditions of Definitions 2 and 3, and (ii) the associated score-based learning objectives designed to promote the corresponding block structure. The classical experiments provide a point of comparison, while the embodied experiments investigate the objectives under less idealized data conditions.
Q6. Supervised rather than unsupervised baseline
RoboPEPP was selected as a state of the art domain-specific deep learning method for pose estimation. That it uses supervised learning additionally enabled us to evaluate performance across different labeling budgets. Our intent was to present RoboPEPP as a practically relevant task-specific reference rather than a generic unsupervised disentanglement baseline.
Q7. Missing block-disentanglement baseline
While we agree that a block-disentanglement baseline is missing, the reconstruction-only case (λ=0) serves as a controlled ablation of the score penalty under the same architecture and kernel-ridge evaluation protocol, making the relative comparison internally consistent. At db=32, active-block R2 increases from 0.23 to 0.61 at λ=50. This provides evidence that the score regularizer improves target-information concentration within our pipeline, but does not establish superiority over other CRL methods or robustness to the choice of evaluation regressor. We will make this distinction explicit.
Q8. One-way regression versus bijection
Under regularity conditions, exact R2(ZI∣Z^I^)=1 is sufficient to rule out the learned block from depending on nuisance information. However, the reviewer is correct: empirically, under non-ideal R2 values the one-sided metric is not sufficient for showing bijectivity/block identification, and we will include the reverse direction R2(Z^I^∣ZI) as well as the metric in [2] in our final revision.
We note that during our initial experiments, we did compute this metric, but did not report them due to the values being generally high (>0.8) in all settings, and thus not being discriminative. We included these values in the new experiments we conducted (see Appendix C.4.4) and showed that its values are mostly saturated.
Q9. Inactive true block
We do compare against a reconstruction-only autoencoder baseline (albeit with db>n) with our method: this corresponds to setting λ=0 in our experiments. Table 2 shows that enabling the score-based regularizer (λ>0) does significantly concentrate the information about the active block to the designated block of our estimator.
Furthermore, in Appendix C.4.4 of the revised paper, we provide experiments where the active block size m is chosen strictly less than latent dimension n=6, specifically for 3 and 5. We observe that when score regularization is set high, both forward and backward R2 metrics increase substantially and come close to the roofline R2 values for that subset, showing improved concentration of target information even when other variations are also present in the data set.