AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Nonparametric Network Models for Link Prediction

Sinead A. Williamson

JMLR 2016 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 42 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
use a mixture of Dirichlet network distributions instead of a single symmetric one (ablation)DND · Macbethtest set log likelihood: −2900.56 -> −1769.74Improved
use a mixture of Dirichlet network distributions instead of a single symmetric one (ablation)DND · Military Disputestest set log likelihood: −5019.35 -> −5000.74Improved
use a mixture of Dirichlet network distributions instead of a single symmetric one (ablation)DND · ENRONtest set log likelihood: −15030.77 -> −9053.68Improved
use MDND instead of IRMnetwork model · Macbethtest set log likelihood: −1941.50 -> −1769.74Improved
use MDND instead of IRMnetwork model · Military Disputestest set log likelihood: −6984.25 -> −5000.74Improved
use MDND instead of MMSBnetwork model · Macbethtest set log likelihood: −3077.22 -> −1769.74Improved
use MDND instead of equiprobable baselinenetwork model · ENRONtest set log likelihood: −16509.75 -> −9053.68Improved
use MDND instead of Dirichlet-multinomial baselinenetwork model · ENRONtest set log likelihood: −15800.01 -> −9053.68Improved

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