AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Learning Bayesian Networks from Ordinal Data

Xiang Ge Luo, Giusi Moffa, Jack Kuipers

JMLR 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning · 7 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
model ordinal data with a latent Gaussian structure via OSEM instead of PC or BDe/BGe methodsstructure learning from ordinal data · Simulated DAGs, ROC of pattern recoveryTPR vs FPRpImproved
use BGe score instead of BDe score for ordinal datahybrid structure learning · Simulated DAGs, ROC of pattern recoveryTPR vs FPRpImproved
increase expected number of ordinal levelsOSEM and BGe · 20 nodes, N=500ROC performanceImproved
increase expected number of ordinal levelshybrid BDe · 20 nodes, N=500ROC performanceHurt
increase Dirichlet concentration nu from 0.8 to 2 (more even thresholds)all hybrid methods · 20 nodes, N=500ROC performanceImproved
denser networks, 2 to 5 expected neighboursall methods · 20 nodes, N=500average TPR: almost 75% at d=2 -> below 75% at d=5Hurt
use OSEM instead of hybrid BDe/BGeruntime · 12, 20, 30 nodes, N=500runtime: less than 10 seconds -> around 1.5, 2.5 and 3.5 minutesHurt
OSEM versus BDe baseline on real datapredictive log loss · five real ordinal datasets, 80/20 splitrelative log lossImproved
use ordinal OPCART instead of PCARTmixed-data structure learning · simulated ordinal datastructure recoveryHurt

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