- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper takes two causal abstraction definitions by Beckers and Halpern in the paper Abstracting Causal Models and examines their relationship in general, non-linear settings.
Strong -abstraction, the weaker of the two definitions in the Beckers and Halpern paper, requires that for every possible high-level intervention, there exist compatible, potentially overlapping low-level interventions. Constructive -abstraction, in addition, requires an injection from low-level micro-variables to high-level macro-variables. Beckers and Halpern predict that constructive abstractions as the ones which will be the most practical, and left the "few minor technical conditions" to go from strong -> constructive to future work.
This paper claims to have the following theoretical contributions
- A counter-example that shows that strong does not implies constructive, under some regularity conditions.
- A proof that strong + intervention-composition-preserving on => constructive, where is the set of all low-level interventions with high-level counterparts.
- A proof that strong + intervention-composition-preserving on <=> constructive, where is the set of low-level interventions that only contains "relevant" low-level variables. A low-level variable is considered relevant if intervening on it by itself corresponds to an intervention in the high-level model.
The paper then follows up with a very small scale experiment on synthetic data, in which the low-level model with state space maps to a high-level model with state space . Variations of of a penalty term that enforces intervention composition preservation at different levels of the model architecture are introduced as a part of the training loss, and shown to reduce prediction MSE.
Critical strengths
The paper demonstrates that a strong abstraction is a non-trivially weaker definition than constructive abstractions in general settings, and exactly characterizes the conditions to go from strong -> constructive as the property intervention-composition-preservation on a relevant set of low-level interventions -- which disproves Beckers and Halpern's conjecture.
Critical weaknesses
- I have some potential doubts about the overall significance of the theoretical results. Beckers and Halpern introduced a sequence of definitions for causal abstractions because they felt that the notion of exact transformations introduced by Rubenstein et al in their paper Causal Consistency of Structural Equation Models was not restrictive enough. The sequence of successively more restrictive definitions ends up being:
exact transformations -> uniform transformations -> abstraction -> strong abstraction -> constructive abstraction
Beckers and Halpern favor the constructive definition as the most useful for practical applications, while conjecturing that the strong definition is very close to it, which motivates the strong definition in the first place. This paper shows that "strong abstraction + intervention compositionality condition = constructive abstraction", which is an interesting result. However, now I'm not sure I see the point in the strong definition, unless it occurs naturally and frequently in practical applications.
-
The presentation of the paper is poor and almost impossible to read without referring to the background literature. In many places, statements are not rigorous where they ought to be and new notation pops up without being defined first (e.g. the opening sentence of Def 2.5). While I think I can understand the main theoretical claims and their underlying intuitions, I have trouble verifying them properly in the time I have allotted for reviewing this paper.
-
The experiment doesn't support the main theoretical results. I might have the wrong interpretation, but the fact that the compositionality penalty lowers the predicted MSE in this particular experimental setup seems to have nothing to do with the definitions of strong nor constructive abstractions. In fact the paper itself states "These finite tests ... do not establish exact constructivity of the trained networks".
Questions for authors
-
Is there a difference between the constructive abstractions given in Def 2.5 of this paper, in comparison to the constructive - abstraction of Beckers and Halpern?
-
How does Def 2.6 relate to the notion of intervention composition given by Lorenz and Tull?
-
Are there natural settings / applications in which the definition of a strong abstraction is more appropriate than the definition of a constructive abstraction?
-
The paper Causal Abstractions, Categorically Unified by Englberger and Dhami claims to "describe examples of strong τ -abstractions that are not constructive τ -abstractions" -- how would you defend the novelty of theorem 1 in this paper against their results?
4 comments
Part 2/2
Question 1
The relationship can be summarized as:
Constructive -abstraction in Beckers and Halpern = constructivity of the mapping (our Definition 2.5) + strong -abstraction.
Our Definition 2.5 isolates the first requirement, constructivity: different high-level variables depend on disjoint sets of low-level variables. Why do we not use Beckers and Halpern's definition of constructive abstraction? Their definition requires strong abstraction, which, as we show in Section 4, excludes many common cases of abstraction. We therefore do not impose this requirement.
And thanks for your question, we will add a brief explanation of this relationship in section 2 of the revised manuscripts for readability.
Question 2
Our definition of intervention composition is the same as Lorenz and Tull's (Example 69(2)): later assignments overwrite earlier ones on shared variables. However, their Proposition 70(a) considers a different setting: it assumes a disjoint variable alignment and studies the induced intervention map on complete aligned blocks. In contrast, our Theorem 3 uses domains defined directly from and its canonical intervention map, without assuming constructivity.
Question 3
As discussed in our response to Weakness 1, our contribution does not rely on strong abstraction being more appropriate than constructive abstraction in applications. We study the original strong-abstraction requirement in Section 3 to address Beckers and Halpern’s conjecture. Section 4 then explains why this requirement can exclude natural aggregations and considers smaller intervention domains while preserving full high-level intervention coverage.
In particular, Theorem 3 does not assume strong abstraction: it characterizes constructivity of the mapping through composition preservation on these restricted domains. Corollary 4 applies this characterization to causal models satisfying interventional consistency on the chosen domain. Thus, our practical motivation is to understand when constructivity follows from intervention requirements on an appropriate domain, rather than to identify applications in which the original strong-abstraction definition should be preferred.
Question 4
Englberger and Dhami (2025) examples shows that strong abstraction need not be constructive. Theorem 1 strengthens this observation in two ways.
1. Counterexamples with substantial regularity.
Beckers and Halpern’s conjecture can be summarized as
For each , Theorem 1 constructs one fixed edgeless low-level SCM that admits every -node DAG as a strong -abstraction. As explained in the construction in Section 3, whenever the high-level DAG contains an edge, the mapping is non-constructive. Moreover, these constructions satisfy some regularity conditions: analytic mechanisms, independent full-support noise blocks, and analytic, surjective abstraction mappings with full-row-rank Jacobians everywhere. Thus,
This identifies substantial regularity conditions that are insufficient to establish the conjectured implication.
2. A graphical consequence of lacking constructivity.
Schooltink and Zennaro (2025) establish connections between low-level and high-level causal graphs under constructive abstraction. For the fixed edgeless low-level SCM constructed in Theorem 1, the contrast is particularly direct:
Constructive abstraction (Schooltink and Zennaro, 2025):
Edgeless low-level SCM + constructive abstraction ⇒ edgeless high-level DAG.
Strong abstraction (our Theorem 1):
Edgeless low-level SCM + strong abstraction ⇒ arbitrary high-level DAG.
Specifically, under constructive abstraction, our edgeless low-level SCM can only correspond to an edgeless high-level DAG. However, weakening the requirement to strong abstraction allows the same fixed SCM to correspond to any high-level DAG on nodes. This illustrates how differently strong and constructive abstraction constrain the correspondence between low- and high-level causal graphs.
Schooltink, W. & Zennaro, F.M.. (2025). Aligning Graphical and Functional Causal Abstractions. CLeaR 2025
Thank you for your detailed responses, in particular the clarification on Thm 3 and your definition of constructivity. My concerns about the practical limitations of strong abstractions (W1) are now resolved, since Thm 3 does not rely on the strong definition.
However, I am now more concerned about the discrepancy between your definition of constructivity and Beckers and Halpern's, as you acknowledged in response to Q1. Given that Beckers and Halpern's definition of constructive causal abstractions is the only widely accepted one in this field, the introduction of a new definition of constructivity should be made very clear in the abstract as well as the introduction, not just with an added sentence in section 2.
This is not to say that I cannot see the motivation behind introducing this new definition, as you have explained in your rebuttal responses. I just think that the framing of this work should be re-assessed. In fact, even the paper title can potentially be seen as misleading, since instead of characterizing the existing definition of constructivity, you re-defined constructivity and shown properties under this new definition.
Additionally, I still maintain that the experiments seem rather superfluous. My concern in W3 was not that "the experiment seems unrelated to the definitions of strong or constructive abstraction", but that the experiments do not validate any of Thms 1-3. Testing whether the composition condition can provide a useful training constraint is an interesting but separate question.
We thank the reviewer for saying that we have addressed Weakness 1. And we want to clarify the point the reviewer is most concerned about because we think there might still be a misunderstanding.
“Given that Beckers and Halpern's definition of constructive causal abstractions is the only widely accepted one in this field, the introduction of a new definition of constructivity […]”
We did not define a new definition of constructivity. As we already said in our previous rebuttal, Beckers and Halpern’s definition of constructive -abstraction can be divided into two parts:
Constructive -abstraction in Beckers and Halpern = constructivity of the mapping (our Definition 2.5) + strong -abstraction.
Of these two parts, strong -abstraction is just a condition on the relation between the two causal models. The concept of “constructivity” is reflected only in the constructivity of the mapping (i.e., the relevant sets are pairwise disjoint: for all ). See Beckers, Eberhardt, and Halpern, Approximate Causal Abstractions, Definition 2.6. There they explicitly say what it means for to be constructive, and this definition does not depend on strong -abstraction.
And we borrow exactly the same definition of constructivity of the mapping.
“the paper title can potentially be seen as misleading, since instead of characterizing the existing definition of constructivity, you re-defined constructivity and shown properties under this new definition.”
As we have said, this is not a “new definition” of constructivity. And we will show more specifically why our title, Characterizing Constructive Causal Abstraction via Intervention Composition, is not misleading even for the readers who only want to see the characterization of constructive tau abstraction in Beckers and Halpern.
Assume there is a reader who likes strong abstraction very much and only cares about Beckers and Halpern’s definition of constructive -abstraction, which requires strong -abstraction. Theorems 1 and 2 follow Beckers and Halpern’s definition of constructive -abstraction exactly, including the strong -abstraction condition. For Theorem 2, we assume strong -abstraction and show that preserving intervention composition on the full canonical domain implies constructive -abstraction in their sense. And for Theorem 3, the fact that it does not rely on strong -abstraction does not mean that the result does not hold under strong -abstraction. If we simply add the strong -abstraction condition to Theorem 3 then we have
Under strong -abstraction between M_L and M_H:
preserves intervention composition on or M_H is a constructive τ-abstraction of M_L in Beckers and Halpern’s definition
The proof is trivial because our original proof of Theorem 3 does not rely on strong -abstraction, and none of its assumptions conflict with strong -abstraction.
Therefore, this reader gets an exact characterization of constructivity under strong -abstraction.
My concern in W3 was not that "the experiment seems unrelated to the definitions of strong or constructive abstraction", but that the experiments do not validate any of Thms 1-3.
We thank the reviewer for emphasizing again the need to make clearer the purpose and limitation of the current experiments, which we tried to do in the updated manuscript, also in response to the other reviewer's comments. Importantly, the purpose of the experiment is not to validate any of the theorems, for as theorems, they need no validation, but rather to demonstrate the potential of designing new learning objectives inspired by the characterization. We agree that the attempt is still very limited and have made this clear in the revised paper.
Part 1/2
Thank you for your thoughtful comments, suggestions and the time you devoted to the review. Below is our response to every weakness and question.
Clarification before response
Thank you for your helpful summary of our paper. We would like to clarify one point about Theorem 3. This may simply be a typo, but we mention it to avoid any possible misunderstanding. Our Theorem 3 is not
Instead, under the assumptions stated in the theorem, it is
The key difference is that Theorem 3 does not require strong abstraction.
Weakness 1
We agree that the practical limitations of strong abstraction deserve attention, and this is part of the motivation for Section 4 in our manuscript. In Section 4, we aim to clarify the limitations of strong abstraction and characterize constructivity on appropriate intervention domains, rather than advocate strong abstraction as a general requirement. Our paper does not recommend that the causal abstraction community continue using strong τ-abstraction and the original definition of constructive abstraction given in Beckers and Halpern's paper. We also do not think that strong abstraction, which requires all compatible low-level interventions to satisfy interventional consistency, “occurs naturally and frequently in practical applications.”
To clarify how this concern relates to our results, we briefly explain the progression of the paper. In Section 3, we first discuss the conjecture using Beckers and Halpern’s definitions of strong abstraction and constructive abstraction. We then find that even the very simple summation case Y = X1 + X2 may violate strong abstraction. Thus, if we use Beckers and Halpern’s definitions, our theoretical results in Section 3 can only apply to limited cases. In Section 4, we therefore move beyond the original strong-abstraction requirement and discuss the conjecture on a more reasonable intervention domain. Section 4.1 illustrates how the original strong-abstraction requirement excludes natural aggregation mappings and motivates considering smaller intervention domains. At the end of Section 4.1, we write, “We therefore recommend stating the intervention domain explicitly when using constructive abstraction” (lines 242–243 in our original manuscript). In Section 4.2, we show that, on a smaller but more reasonable intervention domain, intervention composition preservation is equivalent to constructivity.
Weakness 2
Thank you for pointing out the presentation issue. The opening sentence of Definition 2.5 introduces and defines the notation you mention. We will make this definition more explicit in the revised manuscript.
Weakness 3
The experiment seems unrelated to the definitions of strong or constructive abstraction.
The experiment tests whether the composition condition (equivalent to constructivity) in theorem 3 can provide a useful training constraint. Take Output Comp (Eq. 7) as an example:
LoutComp=3B1∑r=1B∑j=kr[τθ,j(x′(r))−τθ,j(x~(r))]2.
Our theoretical composition condition is
ωτ(i∘k)=ωτ(i)∘ωτ(k).
For sample r, take k=(VL←x~(r)), which fixes all low-level variables, and i=((akr,bkr)←(cr,cr)), which overwrites one input pair. Their composition fixes the low-level state to x′(r).
The left-hand side therefore fixes all high-level variables to τθ(x′(r)). The right-hand side first fixes them to τθ(x~(r)), then overwrites only Ykr with cr. Thus, Comp requires
τθ,j(x′(r))=τθ,j(x~(r)),j=kr.
Therefore we penalize τθ,j(x′(r))−τθ,j(x~(r)) in our loss.
In fact the paper itself states "These finite tests ... do not establish exact constructivity of the trained networks".
The sentence you quote does not mean that the experiment is unrelated to constructivity. Under the assumptions of Theorem 3, the necessary and sufficient condition is i∘k∈D and ωτ(i∘k)=ωτ(i)∘ωτ(k) for all i,k∈D, where D=Jτ or Jτrel. In our experiment, intervention values are continuous, so there are infinitely many possible interventions. In practical we cannot test them all, so we use finitely many sampled checks to see whether the resulting training constraint improves prediction.