AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Markov Blanket and Markov Boundary of Multiple Variables

Xu-Qing Liu, Xin-Sheng Liu

JMLR 2018 · Probabilistic and scientific modeling › Causal discovery · approach: Constraint-based structure learning with latents · 11 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace IAMB-I with MIAMB-III (multi-variable Markov boundary)IAMB · 32-class targetsbalanced accuracy: 0.8683 -> 0.9242Improved
replace IAMB-I with MIAMB-IIIIAMB · 4-class targetsbalanced accuracy: 0.9295 -> 0.9507Improved
replace KIAMB-I with MKIAMB-IIIKIAMB · 32-class targetsbalanced accuracy: 0.8687 -> 0.9239Improved
replace KIAMB-I with MKIAMB-IIIKIAMB · 4-class targetsbalanced accuracy: 0.9283 -> 0.9501Improved
use variant I instead of variant II of IAMB (ablation)IAMB · 4-class targetsbalanced accuracy: 0.9020 -> 0.9295Improved
add the multi-variable approach with variant II to IAMB-IIIAMB-II · 32-class targetsbalanced accuracy: 0.8179 -> 0.9139Improved
use MKIAMB-I instead of KIAMB-IKIAMB-I · 4-class targetsbalanced accuracy: 0.9283 -> 0.9281No clear effect
use MKIAMB-I instead of KIAMB-IKIAMB-I · 32-class targetsbalanced accuracy: 0.8687 -> 0.9111Improved
use MIAMB/MKIAMB instead of IAMB/KIAMB when multiple targets increaseIAMB/KIAMB · Six synthetic BNs, benchmarkingweighted accuracy and running timeImproved
use MIAMB-III instead of MIAMB-II (ablation)MIAMB · 4-class targetsbalanced accuracy: 0.9366 -> 0.9507Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy