mlsanityData to 7 Oct 2026

Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributions

arXiv 2301.05893 ↗First posted 14 Jan 2023cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

An abstraction can be used to relate two structural causal models representing the same system at different levels of resolution. Learning abstractions which guarantee consistency with respect to interventional distributions would allow one to jointly reason about evidence across multiple levels of granularity while respecting the underlying cause-effect relationships. In this paper, we introduce a first framework for causal abstraction learning between SCMs based on the formalization of abstraction recently proposed by Rischel (2020). Based on that, we propose a differentiable programming solution that jointly solves a number of combinatorial sub-problems, and we study its performance and benefits against independent and sequential approaches on synthetic settings and on a challenging real-world problem related to electric vehicle battery manufacturing.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 14 of its 37 references that are in the map. First posted on arXiv 14 Jan 2023.

Builds on

14 of 37 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017Causal Consistency of Structural Equation Modelscited by 114
  4. 2018Abstracting Causal Modelscited by 104
  5. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  6. 2019Approximate Causal Abstractioncited by 62
  7. 2019A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statisticscited by 55
  8. 2021Understanding the role of importance weighting for deep learningcited by 38
  9. 2021Compositional Abstraction Error and a Category of Causal Modelscited by 32
  10. 2015The Hamming Ball Samplercited by 16
  11. 2022Abstraction between Structural Causal Models: A Review of Definitions and Propertiescited by 14
  12. 2022On the Equivalence of Causal Models: A Category-Theoretic Approachcited by 13
2 more
  1. 2021Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMCcited by 7
  2. 2022Towards Computing an Optimal Abstraction for Structural Causal Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 4; 2026: 6.

21 papers.

Sort:

  1. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  2. 2023Targeted Reduction of Causal Modelscited by 15
  3. 2023Causal Optimal Transport of Abstractionscited by 13
  4. 2024Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environmentcited by 12
  5. 2024Learning Causal Abstractions of Linear Structural Causal Modelscited by 9
  6. 2025Causal Abstraction Learning based on the Semantic Embedding Principlecited by 9
  7. 2023Quantifying Consistency and Information Loss for Causal Abstraction Learningcited by 6
  8. 2023Interventionally Consistent Surrogates for Agent-based Simulatorscited by 6
  9. 2024Aligning Graphical and Functional Causal Abstractionscited by 6
  10. 2024Causally Abstracted Multi-armed Banditscited by 5
  11. 2024The Causal Information Bottleneck and Optimal Causal Variable Abstractionscited by 4
  12. 2025Combining Causal Models for More Accurate Abstractions of Neural Networkscited by 4
9 more
  1. 2026Structural Causal Bottleneck Modelscited by 4
  2. 2025Distributionally Robust Causal Abstractionscited by 3
  3. 2026Coarsening Causal DAG Modelscited by 2
  4. 2023Do Not Marginalize Mechanisms, Rather Consolidate!cited by 1
  5. 2025Causal Counterfactuals Reconsideredcited by 1
  6. 2026Multi-Level Causal Embeddingscited by 0
  7. 2026Causal Representation Learning for Generalisable Recommendationcited by 0
  8. 2026Unsupervised Causal Abstractions Discoverycited by 0
  9. 2026Validating Causal Abstraction Metrics on Simulated Complex Systemscited by 0