Research map / Probabilistic and scientific modeling / Causal discovery
Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis
Ronan Perry, Julius Von Kügelgen, Bernhard Schölkopf
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use pairwise MSS score instead of pooled PC with oracle tests | MSS · random DAGs, 6 variables, density 0.3, 5 environments | recall | Improved |
| very sparse or very dense mechanism shifts | oracle MSS · random DAGs | recall | Hurt |
| use Fisher-Z test instead of nonparametric KCI or GAM tests (ablation) | MSS estimator · nonlinear simulation | recall and precision | Hurt |
| use soft p-value-based score instead of hard thresholded score (ablation) | MSS with KCI · nonlinear simulation | recall and precision | Mixed |
| MSS with KCI versus pooled PC | MSS · multi-environment simulation | recall and precision | Improved |
| MSS with KCI versus parametric Minimal Changes (MC) | MSS · multi-environment simulation | precision and recall | Improved |
| hub (scale-free) DAG model instead of Erdos-Renyi | oracle MSS vs pooled PC · random DAGs | recall gap | Mixed |
| larger DAGs or denser edges | oracle MSS vs pooled PC · random DAGs, 5 environments | recall difference | Hurt |
Closest papers by meaning
- Identifying Structural Biases from Causal Mechanism Shifts (NeurIPS 2026 · similarity 0.90)
- Identifying General Mechanism Shifts in Linear Causal Representations (NeurIPS 2024 · similarity 0.90)
- Causal learning with the invariance principle (NeurIPS 2026 · similarity 0.90)
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 2025 · similarity 0.90)
- Learning Mixtures of Unknown Causal Interventions (NeurIPS 2024 · similarity 0.89)
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
