Research map / Probabilistic and scientific modeling / Causal discovery
Use What You Know: Causal Foundation Models with Partial Graphs
Arik Reuter, Anish Dhir, Cristiana Diaconu, Jake Robertson, Ole Ossen, Frank Hutter, Adrian Weller, Mark van der Wilk, 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 |
|---|---|---|---|
| condition on partially known ancestral matrix encoding unconfoundedness (ablation) | CFM on complex prior · RealCause IHDP | sqrt(PEHE): 6.28 -> 5.49 | Improved |
| condition on partially known ancestral matrix (ablation) | CFM on complex prior · RealCause ACIC | ATE relative error: 0.46 -> 0.17 | Improved |
| condition on partially known ancestral matrix (ablation) | CFM on complex prior · RealCause CPS | sqrt(PEHE): 12800 -> 11213 | Improved |
| condition on ancestral information (ablation) | CFM on complex prior · RealCause PSID (unbalanced) | sqrt(PEHE): 13096 -> 12975 | Improved |
| add ancestral information (ATE error) (ablation) | CFM on complex prior · RealCause PSID (unbalanced) | ATE relative error: 0.98 -> 1.09 | Hurt |
| soft learnable attention bias instead of hard masking (ablation) | graph-conditioned CFM · linear-Gaussian prior | NLL/MSE/R2 | Improved |
| add GCN encoder to soft attention bias (ablation) | graph-conditioned CFM · complex TFM prior | NLL | Improved |
| use ancestor matrix instead of adjacency matrix (ablation) | soft-attention conditioning · linear-Gaussian prior | MSE and R2: small | Improved |
| hide most ancestor entries at test time (ablation) | graph-conditioned CFM · complex TFM prior | MSE and R2 | Hurt |
| amortise over varying amounts of ancestral information (ablation) | amortised CFM · complex TFM prior | performance | No clear effect |
| misspecify edges instead of marking unknown (ablation) | graph-conditioned CFM · misspecification study | performance | Hurt |
Closest papers by meaning
- Local Identifying Causal Relations in the Presence of Latent Variables (ICML 2025 · similarity 0.89)
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 2025 · similarity 0.88)
- CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery (NeurIPS 2026 · similarity 0.88)
- Causal learning with the invariance principle (NeurIPS 2026 · similarity 0.88)
- Causality can systematically address the monsters under the bench(marks) (NeurIPS 2026 · similarity 0.88)
- Towards Causal Foundation Model: on Duality between Optimal Balancing and Attention (ICML 2024 · similarity 0.87)
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.
