AI Paper Atlas

Research map / Graph learning / GNN architectures

Neural Link Prediction with Walk Pooling

Liming Pan, Cheng Shi, Ivan Dokmanić

ICLR 2022 · Graph learning › GNN architectures · approach: Graph structure learning · 12 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 WalkPool with distance labels instead of WalkPool with all-ones input featuresWalkPool · USAir, NS, PB, Yeast, C.ele, Power, Router, E.coliAUC: 98.52±0.50 -> 98.68±0.48; 98.86±0.42 -> 98.95±0.41; 95.42±0.39 -> 95.60±0.37; 98.16±0.33 -> 98.37±0.25; 92.42±1.22 -> 92Improved
Add WalkPool to unsupervised GNN representationsVGAE, ARGVA, and GIC · Cora, Citeseer, Pubmed, Chameleon, Cornell, Texas, WisconsinAUC: 91.98±0.54 -> 94.64±0.55; 91.21±1.14 -> 94.32±0.90; 96.51±0.14 -> 98.49±0.13; 98.79±0.18 -> 99.51±0.08; 70.59±9.03 -> 78Improved
Remove the ω₁₂ feature (ablation)WalkPool · C.eleAUC: 92.82 -> 92.69Hurt
Remove node-walk features (ablation)WalkPool · C.eleAUC: 92.82 -> 92.66Hurt
Remove link-walk features (ablation)WalkPool · C.eleAUC: 92.82 -> 91.08Hurt
Remove graph-walk features (ablation)WalkPool · C.eleAUC: 92.82 -> 92.65Hurt
Use the final-layer embedding only instead of concatenating initial and GCN-layer embeddings (ablation)WalkPool · Link prediction datasets with node attributesAUCHurt
Increase the walk-length cutoff beyond τc = 7 (ablation)WalkPool · Link prediction benchmarksaccuracyNo clear effect
Use BCE loss instead of MSE loss (ablation)WalkPool · Eight datasets without node attributesAUC: 98.68/98.68; 98.95/98.85; 95.60/95.69; 98.37/98.37; 92.79/92.83; 92.56/92.58; 97.27/97.35; 98.58/98.67No clear effect

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