Research map / Probabilistic and scientific modeling / Causal discovery
The Causal-Neural Connection: Expressiveness, Learnability, and Inference
Kevin Muyuan Xia, Kai-Zhan Lee, Yoshua Bengio, Elias Bareinboim
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 |
|---|---|---|---|
| add causal-diagram inductive bias (G-constrained NCM) vs naive generative model fit by likelihood only | NCM · identifiable SCMs (back-door, front-door, M, napkin) | ATE MAE | Improved |
| use NCM instead of naive model for fitting P(V) | NCM · identifiable SCMs | KL divergence of P(V) | No clear effect |
| use NCM instead of WERM for ATE estimation | NCM · identifiable SCMs | ATE MAE | No clear effect |
| train longer (up to 3000 epochs) when classifying identifiability via max-min gap | NCM identification test · identifiable graphs | classification accuracy | Improved |
| vary threshold tau (0.01, 0.03, 0.05) in identifiability hypothesis test (ablation) | NCM identification test · 8 graphs | classification accuracy | Mixed |
Closest papers by meaning
- Consistency of Neural Causal Partial Identification (NeurIPS 2024 · similarity 0.91)
- Towards Learning and Explaining Indirect Causal Effects in Neural Networks (AAAI 2024 · similarity 0.91)
- Causal learning with the invariance principle (NeurIPS 2026 · similarity 0.90)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.89)
- Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery (ICML 2025 · similarity 0.89)
- Learning Structural Causal Models from Ordering: Identifiable Flow Models (AAAI 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.
