AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Stochastic Blockmodels meet Graph Neural Networks

Nikhil Mehta, Lawrence Carin Duke, Piyush Rai

ICML 2019 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 16 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 nonlinear encoder and decoder to the LFRM-style modelDGLFRM-B vs LFRM · NIPS12AUC ROC: 0.8489 \pm .0001 -> 0.8898\pm.0028Improved
add nonlinear encoder and decoder to the LFRM-style modelDGLFRM-B vs LFRM · CoraAUC ROC: 0.9096\pm.0026 -> 0.9281\pm.0024Improved
use sparse real-valued membership strengths instead of binary-only embeddings (ablation)DGLFRM · CiteseerAUC ROC: 0.9007\pm.0020 -> 0.9379\pm.0032Improved
use sparse real-valued membership strengths instead of binary-only embeddings (ablation)DGLFRM · CoraAverage Precision: 0.9259\pm.0023 -> 0.9376\pm.0022Improved
use binary embeddings instead of sparse real-valued embeddings (ablation)DGLFRM · NIPS12AUC ROC: 0.8734\pm.0043 -> 0.8898\pm.0028Improved
use binary embeddings instead of sparse real-valued embeddings (ablation)DGLFRM · YeastAUC ROC: 0.7856\pm.0005 -> 0.8061\pm.0003Improved
use binary embeddings instead of sparse real-valued embeddings (ablation)DGLFRM · PubmedAUC ROC: 0.9395\pm.0008 -> 0.9396\pm.0052No clear effect
include node features rather than ignoring them (ablation)DGLFRM · Cora, Citeseer, and PubmedAUC ROCImproved
use structured mean-field instead of vanilla mean-field inference (ablation)DGLFRM · link prediction experimentslink prediction performanceImproved

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