- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This study proposes a new framework for causal representation learning (CRL) in a multi-view setting. Unlike existing multi-view CRL methods, it addresses a setting in which group assignments are unobserved, random, and sample-dependent. The study shows that the latent variables are group-identifiable if the encoder achieves the proposed bilevel Disc-InfoMax objective. It also proposes a practical estimation framework for learning shared latent variables and the corresponding mask simultaneously while avoiding feature collapse through Bayesian mask inference and bandwidth annealing of the gating function. The numerical experiments show that the proposed framework outperforms non-multi-view baselines and achieves performance close to that of a multi-view baseline with true grouping labels in some settings.
Critical strengths
-
This study proposes a novel condition for (block) identifiability in multi-view CRL that does not require known grouping labels. Since grouping indices are not given in advance in many practical cases, the framework could be useful in such settings.
-
This study provides a practical estimation framework for learning an encoder from paired observations by minimizing their alignment mismatch. A gating mechanism (proximity mask) focuses on shared latent variables while avoiding feature collapse.
Critical weaknesses
-
This study does not provide a consistency guarantee for the estimation framework.
-
Related to the above, the estimation framework relies on inner–outer bilevel optimization, which seems unstable and does not scale well to higher-dimensional latent variables (Fig. 3 and Table 8). This raises questions about the applicability of the framework to more realistic data with potentially larger numbers of latent variables.
Questions for authors
None.
3 comments
Dear Reviewer,
We would like to thank you again for the insightful review. We have provided a detailed answer in the rebuttal as well as the modified paper. We hope to have resolved all your concerns and will be happy to discuss further if any concerns do remain.
Regards,
Authors
I appreciate the authors' rebuttal. The added consistency theorem addresses my concern in principle. However, the assumptions and conditions required for the consistency guarantee should be stated and discussed more clearly in the main text so that readers can assess the scope of the result. It would also be helpful if the authors provided a more detailed and accessible proof, as the current presentation makes it difficult to follow the argument. Overall, I maintain my score.
Dear reviewer RP1K,
Thank you for your thoughtful review and for considering our work to be well-written and acknowledging our contribution on the novel setup and the corresponding practical algorithm.
Based on your constructive feedback, we have made a revision. All modifications addressing your review are color-coded in orange in the revised paper. Below is our response on each of your points of weaknesses.
1. Statistical Consistency Guarantee for the Empirical Estimator (W1)
To address your concern regarding the consistency guarantee, we have added a formal Statistical Consistency Theorem in Appendix B.3. (Theorem 3). It establishes that the finite-sample empirical estimator consistently converges to the population-level block-identifiable optimum as sample size N→∞. Below is the summary of Appendix B.3.
Theorem 3 (Informal): Under a coupled bandwidth schedule satisfying limN→∞σN=0+ and limN→∞σNN=∞, the empirical minimizer θ^N∈θ∈Θarg,minLN(gθ,t;σN) satisfies:
dist(θ^N,Θ∗_0+)p0as N→∞,
and the limiting encoder induced by any accumulation point block-identifies the shared causal variables CS.
Proof Sketch (Appendix B.3):
2. High-Dimensional Scaling & Dataset Difficulty (W2)
We clarify that the lower metrics observed at n=16 and n=32 reflect the difficulty of the synthetic validation benchmark, rather than an intrinsic failure of BayesDisc in higher dimensions:
We hope to have clarified most of your stated concerns. Please let us know if there are any additional information we can provide to further clarify our contributions. Thank you once again for your time and effort for reviewing our paper!
Kindly,
Authors