AI Paper Atlas

Research map / Graph learning / GNN architectures

Line Graph Neural Networks for Link Prediction

Lei Cai, Jundong Li, Jie Wang, Shuiwang Ji

TPAMI 2021 · Graph learning › GNN architectures · approach: Graph structure learning · 259 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
learn link features in the line graph instead of enclosing-subgraph classification with pooling (LGLP vs SEAL)link prediction GNN · C.ele (80% training links)AUC: 87.44 -> 90.16Improved
learn link features in the line graph (LGLP vs SEAL)link prediction GNN · BUP (50% training links)AUC: 85.10 -> 88.57Improved
learn link features in the line graph (LGLP vs SEAL)link prediction GNN · EML (80% training links)AUC: 92.01 -> 92.03No clear effect
add node attributes as inputSEAL · Cora (50% training links)AUC: 79.95 -> 75.33Hurt
add node attributes as inputLGLP · Cora (50% training links)AUC: 79.96 -> 81.45Improved
add node attributes with LGLP combination function instead of SEAL concatenationlink prediction GNN · Cora with attributes (50% training links)AUC: 75.33 -> 81.45Improved
reduce training links from 80% to 50%LGLP · USAirAUC: 97.44 -> 95.18Hurt
reduce training links from 80% to 50%SEAL · USAirAUC: 95.21 -> 93.23Hurt
use line graph with graph convolution only, no pooling, instead of SEAL poolingLGLP · training convergenceepochs: 50 -> 10 to 15Improved

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