Research map / Probabilistic and scientific modeling / Causal discovery
Learning Causal Models under Independent Changes
Sarah Mameche, David Kaltenpoth, Jilles Vreeken
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 LINC instead of MSS | edge orientation · Sachs cell signalling | F1: 0.83 -> 0.90 | Improved |
| use LINC instead of Minimal Changes (MC) | edge orientation · Sachs cell signalling | F1: 0.68 -> 0.90 | Improved |
| use LINC instead of Pooled PC | edge orientation · Sachs cell signalling | F1: 0.75 -> 0.90 | Improved |
| use LINC instead of Pooled PC with no mechanism shifts (i.i.d. data) | edge orientation · synthetic, |S|=0 | F1 | Improved |
| use LINC instead of Pooled PC | edge orientation · synthetic, |C|=5, |G|=6, |S|=2 | F1 | Improved |
| replace Gaussian process with random Fourier feature approximation (LINC-RFF) (ablation) | LINC · synthetic | F1 | No clear effect |
| use hard interventions (gene knockouts) instead of soft interventions | MSS · SERGIO gene expression | F1 | Hurt |
| use dense shifts (|S|=|C|) or no shifts instead of sparse shifts | MSS and MC · synthetic | F1 | Hurt |
| increase number of conditions | LINC · SERGIO gene expression | F1 | Improved |
| replace exhaustive partition search with clustering (LINC-CLUS) (ablation) | LINC · synthetic scalability | runtime | Improved |
Closest papers by meaning
- Learning Mixtures of Unknown Causal Interventions (NeurIPS 2024 · similarity 0.90)
- Causal Discovery with Fewer Conditional Independence Tests (ICML 2024 · similarity 0.89)
- Signature Kernel Conditional Independence Tests in Causal Discovery for Stochastic Processes (ICLR 2025 · similarity 0.89)
- Systems with Switching Causal Relations: A Meta-Causal Perspective (ICLR 2025 · similarity 0.89)
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 2025 · similarity 0.89)
- Characterization and Learning of Causal Graphs from Hard Interventions (NeurIPS 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.
