Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions

Panayiotis Panayiotou, Özgür Şimşek

Abstract

Causal discovery is challenging in general dynamical systems because, without strong structural assumptions, the underlying causal graph may not be identifiable even from interventional data. However, many real-world systems exhibit directional, cascade-like structure, in which components activate sequentially and upstream failures suppress downstream effects. We study causal discovery in such chain-reaction systems and show that the causal structure is uniquely identifiable from blocking interventions that prevent individual components from activating. We propose a minimal estimator with finite-sample guarantees, achieving exponential error decay and logarithmic sample complexity. Experiments on synthetic models and diverse chain-reaction environments demonstrate reliable recovery from a few interventions, while observational heuristics fail in regimes with delayed or overlapping causal effects.

Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions

Abstract

Causal discovery is challenging in general dynamical systems because, without strong structural assumptions, the underlying causal graph may not be identifiable even from interventional data. However, many real-world systems exhibit directional, cascade-like structure, in which components activate sequentially and upstream failures suppress downstream effects. We study causal discovery in such chain-reaction systems and show that the causal structure is uniquely identifiable from blocking interventions that prevent individual components from activating. We propose a minimal estimator with finite-sample guarantees, achieving exponential error decay and logarithmic sample complexity. Experiments on synthetic models and diverse chain-reaction environments demonstrate reliable recovery from a few interventions, while observational heuristics fail in regimes with delayed or overlapping causal effects.
Paper Structure (37 sections, 4 theorems, 25 equations, 15 figures, 7 tables, 1 algorithm)

This paper contains 37 sections, 4 theorems, 25 equations, 15 figures, 7 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Contributions.
  3. Related Work
  4. Causal discovery with interventions.
  5. Causal discovery under structural and invariance assumptions.
  6. Deterministic and cascade-style propagation models.
  7. Problem Setup
  8. Preliminaries
  9. Chain-Reaction Causal Model
  10. Monotone Cascade Structural Causal Model
  11. Interventions and Data Collection
  12. Learning Objective
  13. Method
  14. Identifiability from Blocking Interventions
  15. Estimation from a Finite Interventional Dataset
  16. ...and 22 more sections

Key Result

lemma 1

For any $i \neq j$,

Figures (15)

  • Figure 1: Causal discovery in a chain-reaction system. Directed edges represent causal responsibility rather than low-level physical forces. Holding an object in place breaks the chain reaction and deterministically suppresses all downstream activations, revealing ancestor--descendant relations.
  • Figure 2: Collection of environments used for evaluation.
  • Figure 3: Scaling with the number of blocking interventions per object. (Left) Average skeleton SHD as a function of the number of interventions. (Right) Probability of exact recovery. Each curve corresponds to one environment evaluated at its largest feasible displacement $\Delta$. We see strong sample efficiency.
  • Figure 4: Scaling with the number of blocking interventions per object on synthetic SCMs (Left) Average skeleton SHD. (Right) Probability of exact recovery. In this controlled setting, skeleton SHD decays exponentially, and recovery probability increases exponentially with the number of interventions, in agreement with the finite-sample guarantees of Theorem \ref{['thm:sample']}. The number suffix denotes the Bernoulli failure parameter.
  • Figure 5: Observational rollout of Minimal Chain
  • ...and 10 more figures

Theorems & Definitions (7)

  • lemma 1: Deterministic cascade relation
  • proof
  • theorem 1: Identifiability
  • proof
  • theorem 2: Sample Complexity
  • corollary 1: Exact Tree Recovery
  • proof