AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Causal Discovery with Generalized Linear Models through Peeling Algorithms

Minjie Wang, Xiaotong Shen, Wei Pan

JMLR 2024 · Probabilistic and scientific modeling › Causal discovery · approach: Interventional causal discovery · 0 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
add GAMPI instead of NOTEARSNOTEARS · Binary outcomes, hub graph (100,100,500)F-score: 0.16 -> 0.96Improved
add GAMPI instead of NOTEARSNOTEARS · Binary outcomes, hub graph (100,100,500)SHD: 90.30 -> 8.10Improved
add GAMPI instead of NOTEARSNOTEARS · Binary outcomes, chain graph (300,300,500)SHD: 224.80 -> 84.30Improved
add GAMPI instead of NOTEARSNOTEARS · Binary outcomes, random graph (300,300,500)SHD: 224.30 -> 144.00Improved
add GAMPI instead of NOTEARSNOTEARS · Count outcomes, hub graph (300,300,500)SHD: 299.00 -> 2.50Improved
add GAMPI instead of NOTEARSNOTEARS · Count outcomes, random graph (300,300,500)SHD: 228.60 -> 49.20Improved
add deconfounding (DRI) instead of standard logistic regression (ablation)GAMPI peeling algorithm · Binary outcomes, chain graph with confoundersgraph recoveryImproved
add GAMPI instead of DAGMADAGMA · Binary/Gaussian outcomes, simulated graphsgraph recoveryImproved
increase graph size from 100 to 300 nodesGAMPI · Binary outcomes, random graphF-score: 0.74 -> 0.64Hurt

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