AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information

T. Tony Cai, Tengyuan Liang, Alexander Rakhlin

JMLR 2020 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features

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
increase message passing depth from 2 to 4 (ablation)AMP · Political blogs, delta=0.1misclassification error: 6.31% -> 5.01%Improved
increase message passing depth from 2 to 4 (ablation)AMP · Political blogs, delta=0.05misclassification error: 7.71% -> 5.08%Improved
increase message passing depth from 2 to 4 (ablation)AMP · Political blogs, delta=0.025misclassification error: 10.20% -> 5.66%Improved
use AMP depth 4 instead of spectral algorithmAMP · Political blogs, delta=0.1misclassification error: 6.68% -> 5.01%Improved
use AMP depth 4 instead of spectral algorithmAMP · Political blogs, delta=0.025misclassification error: 6.63% -> 5.66%Improved
use AMP depth 2 instead of spectral algorithmAMP · Political blogs, delta=0.05misclassification error: 6.66% -> 7.71%Hurt
reduce revealed label fraction from 0.1 to 0.025AMP depth 4 · Political blogsmisclassification error: 5.01% -> 5.66%Hurt
use AMP instead of degree-corrected SCOREAMP · Political blogsmisclassification error: 4.75% -> 5.01%Hurt

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