Research map / Probabilistic and scientific modeling / Causal discovery
Integrating Markov Blanket Discovery into Causal Representation Learning for Domain Generalization
Naiyu Yin, Hanjing Wang, Yue Yu, Tian Gao, Amit Dhurandhar, Qiang Ji
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 |
|---|---|---|---|
| select the full latent Markov Blanket set instead of only parent variables (ablation) | CMBRL · Colored MNIST OOD | accuracy (%): 69.8 -> 74.1 | Improved |
| use CMBRL instead of ERM, which fits spurious color correlations | Colored MNIST · Colored MNIST OOD | accuracy (%): 10.3 -> 74.1 | Improved |
| use CMBRL instead of ERM on in-distribution data | Colored MNIST · Colored MNIST in-distribution | accuracy (%): 85.7 -> 76.4 | Hurt |
| use CMBRL instead of the second-best baseline iCaRL on CelebA | CelebA OOD · CelebA OOD (avg over 7 settings) | accuracy (%): 71.5 -> 76.2 | Improved |
| use CMBRL instead of iCaRL on VLCS and PACS | domain generalization · VLCS and PACS (ResNet50) | average accuracy (%): VLCS 81.8 -> 82.3; PACS 88.7 -> 89.1 | Improved |
| use NF-iVAE prior in phase I instead of VAE or iVAE | CMBRL · Colored MNIST | MCC (identifiability) | Improved |
| use CMBRL against IRM variants with only two training domains | Colored MNIST · Colored MNIST OOD | accuracy (%): 62.8 -> 74.1 | Improved |
Closest papers by meaning
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.89)
- A Sparsity Principle for Partially Observable Causal Representation Learning (ICML 2024 · similarity 0.88)
- Causal Representation Learning Made Identifiable by Grouping of Observational Variables (ICML 2024 · similarity 0.88)
- Causal Representation Learning from Multiple Distributions: A General Setting (ICML 2024 · similarity 0.88)
- Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains (ICML 2025 · similarity 0.88)
- Multi-View Causal Representation Learning with Partial Observability (ICLR 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.
