Research map / Probabilistic and scientific modeling / Causal discovery
Large-Scale Differentiable Causal Discovery of Factor Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Constrain causal graphs to low-rank factor DAGs | DCD-FG · Linear Gaussian SCM simulations | Interventional NLL | Helped |
| Constrain causal graphs to low-rank factor DAGs | DCD-FG · Linear Gaussian SCM simulations | SHD | Helped |
| Constrain causal graphs to low-rank factor DAGs | DCD-FG · Nonlinear NN SCM simulations | Interventional NLL | Helped |
| Constrain causal graphs to low-rank factor DAGs | DCD-FG · Nonlinear NN SCM simulations | Recall | Helped |
| Constrain causal graphs to low-rank factor DAGs | DCD-FG · Nonlinear NN SCM simulations | SHD | Mixed |
| Use DCD-FG instead of NOTEARS variants | Causal discovery on Perturb-CITE-seq · Perturb-CITE-seq melanoma cells, held-out interventions | Interventional NLL | Helped |
| Use DCD-FG instead of NOTEARS variants | Causal discovery on Perturb-CITE-seq · Perturb-CITE-seq melanoma cells, held-out interventions | Interventional MAE | Helped |
| Use DCD-FG instead of IGSP | Causal discovery on Perturb-CITE-seq · Perturb-CITE-seq melanoma cells, held-out interventions | Interventional NLL | Helped |
| Use correlated factor-edge samples to prevent induced self-loops (ablation) | DCD-FG · Causal graph sampling | Model performance | Helped |
| Replace a full-input neural conditional model with factor-level MLPs and linear output from parent factors (ablation) | DCD-FG · High-dimensional interventional causal discovery | Runtime | Helped |
Closest papers by meaning
- Interventional Causal Discovery in a Mixture of DAGs (NeurIPS 2024 · similarity 0.92)
- Differentiable Cyclic Causal Discovery Under Unmeasured Confounders (NeurIPS 2025 · similarity 0.91)
- Stable Differentiable Causal Discovery (ICML 2024 · similarity 0.91)
- Differentiable Causal Discovery for Latent Hierarchical Causal Models (ICLR 2025 · similarity 0.91)
- A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables (ICLR 2024 · similarity 0.90)
- CausalTab: Pretraining Across Causal Environments for Tabular Causal Discovery (NeurIPS 2026 · similarity 0.90)
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.