mlsanityData to 7 Oct 2026

Targeted Reduction of Causal Models

arXiv 2311.18639 ↗First posted 30 Nov 2023stat.ML cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Why does a phenomenon occur? Addressing this question is central to most scientific inquiries and often relies on simulations of scientific models. As models become more intricate, deciphering the causes behind phenomena in high-dimensional spaces of interconnected variables becomes increasingly challenging. Causal Representation Learning (CRL) offers a promising avenue to uncover interpretable causal patterns within these simulations through an interventional lens. However, developing general CRL frameworks suitable for practical applications remains an open challenge. We introduce Targeted Causal Reduction (TCR), a method for condensing complex intervenable models into a concise set of causal factors that explain a specific target phenomenon. We propose an information theoretic objective to learn TCR from interventional data of simulations, establish identifiability for continuous variables under shift interventions and present a practical algorithm for learning TCRs. Its ability to generate interpretable high-level explanations from complex models is demonstrated on toy and mechanical systems, illustrating its potential to assist scientists in the study of complex phenomena in a broad range of disciplines.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

23 of 37 references.

References · 23

  1. 2021Causal Abstractions of Neural Networkscited by 401
  2. 2023Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationscited by 197
  3. 2023Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretabilitycited by 194
  4. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  5. 2016Foundations of Structural Causal Models with Cycles and Latent Variablescited by 134
  6. 2017Causal Consistency of Structural Equation Modelscited by 114
  7. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  8. 2018Abstracting Causal Modelscited by 104
  9. 2022Linear Causal Disentanglement via Interventionscited by 84
  10. 2019Causal structure based root cause analysis of outlierscited by 65
  11. 2019Approximate Causal Abstractioncited by 62
  12. 2014Visual Causal Feature Learningcited by 59
11 more
  1. 2023Causal Component Analysiscited by 56
  2. 2018Counterfactuals uncover the modular structure of deep generative modelscited by 51
  3. 2014From Ordinary Differential Equations to Structural Causal Models: the deterministic casecited by 41
  4. 2021Compositional Abstraction Error and a Category of Causal Modelscited by 32
  5. 2022Causal Abstraction with Soft Interventionscited by 23
  6. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 21
  7. 2016Unsupervised Discovery of El Nino Using Causal Feature Learning on Microlevel Climate Datacited by 19
  8. 2022Backtracking Counterfactualscited by 15
  9. 2020Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layerscited by 13
  10. 2023Meaningful Causal Aggregation and Paradoxical Confoundingcited by 5
  11. 2021Learning soft interventions in complex equilibrium systemscited by 2

Built on by

Cited by year (2026 to 7 Oct)

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

15 papers.

Sort:

  1. 2024Learning Causal Abstractions of Linear Structural Causal Modelscited by 9
  2. 2025Causal Abstraction Learning based on the Semantic Embedding Principlecited by 9
  3. 2024Aligning Graphical and Functional Causal Abstractionscited by 6
  4. 2025What is causal about causal models and representations?cited by 6
  5. 2025Combining Causal Models for More Accurate Abstractions of Neural Networkscited by 4
  6. 2025Distributionally Robust Causal Abstractionscited by 3
  7. 2024Systems with Switching Causal Relations: A Meta-Causal Perspectivecited by 2
  8. 2026Coarsening Causal DAG Modelscited by 2
  9. 2024Linear causal disentanglement via higher-order cumulantscited by 1
  10. 2025Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policiescited by 1
  11. 2024Causal Learning in Biomedical Applications: Krebs Cycle as a Benchmarkcited by 0
  12. 2025Learning Joint Interventional Effects from Single-Variable Interventions in Additive Modelscited by 0
3 more
  1. 2026Causal Representation Learning for Generalisable Recommendationcited by 0
  2. 2026Unsupervised Causal Abstractions Discoverycited by 0
  3. 2026Validating Causal Abstraction Metrics on Simulated Complex Systemscited by 0