mlsanityData to 7 Oct 2026

Structural Causal Bottleneck Models

arXiv 2603.08682 ↗First posted 9 Mar 2026stat.ML cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce structural causal bottleneck models (SCBMs), a novel class of structural causal models. At the core of SCBMs lies the assumption that causal effects between high-dimensional variables only depend on low-dimensional summary statistics, or bottlenecks, of the causes. SCBMs provide a flexible framework for task-specific dimension reduction while being estimable via standard, simple learning algorithms in practice. We analyse identifiability in SCBMs, connect them to information bottlenecks in the sense of Tishby & Zaslavsky (2015), and illustrate how to estimate them experimentally. We also demonstrate the benefit of bottlenecks for effect estimation in low-sample transfer learning settings. We argue that SCBMs provide an alternative to existing causal dimension reduction frameworks like causal representation learning or causal abstraction learning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

26 of 50 references.

References · 26

  1. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  2. 2022Weakly supervised causal representation learningcited by 140
  3. 2022Interventional Causal Representation Learningcited by 140
  4. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  5. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  6. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
  7. 2022Linear Causal Disentanglement via Interventionscited by 84
  8. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 72
  9. 2023Causal Component Analysiscited by 56
  10. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 50
  11. 2023Score-based Causal Representation Learning with Interventionscited by 49
  12. 2024Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependenciescited by 39
14 more
  1. 2023BISCUIT: Causal Representation Learning from Binary Interactionscited by 38
  2. 2022Causal Inference Through the Structural Causal Marginal Problemcited by 22
  3. 2023Jointly Learning Consistent Causal Abstractions Over Multiple Interventional Distributionscited by 21
  4. 2023Foundations of Causal Discovery on Groups of Variablescited by 20
  5. 2024Neural Causal Abstractionscited by 20
  6. 2023Identifying Linearly-Mixed Causal Representations from Multi-Node Interventionscited by 18
  7. 2021Necessary and sufficient graphical conditions for optimal adjustment sets in causal graphical models with hidden variablescited by 16
  8. 2023Causal Optimal Transport of Abstractionscited by 13
  9. 2024Learning Causal Abstractions of Linear Structural Causal Modelscited by 9
  10. 2025Causal Abstraction Learning based on the Semantic Embedding Principlecited by 9
  11. 2025What is causal about causal models and representations?cited by 6
  12. 2025Sanity Checking Causal Representation Learning on a Simple Real-World Systemcited by 5
  13. 2025Causal discovery on vector-valued variables and consistency-guided aggregationcited by 3
  14. 2024DecoR: Deconfounding Time Series with Robust Regressioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretationcited by 1
  2. 2026Causal Representation Learning for Generalisable Recommendationcited by 0
  3. 2026Unsupervised Causal Abstractions Discoverycited by 0
  4. 2026Score-Based Learning of Cluster DAGs from Interventionscited by 0