AI Paper Atlas

Research map / Graph learning / GNN architectures

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Seongjun Yun, Seoyoon Kim, Junhyun Lee, Jaewoo Kang, Hyunwoo J. Kim

NeurIPS 2021 · Graph learning › GNN architectures · approach: Simple and scalable GNNs · 46 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 GCN score combined via learnable alpha to Neo-GNN (ablation)Neo-GNN · OGB-DdiHits@20: 17.38 -> 63.57Improved
add GCN score combination to Neo-GNN (ablation)Neo-GNN · OGB-CollabHits@50: 55.70 -> 57.52Improved
add GCN score combination to Neo-GNN (ablation)Neo-GNN · OGB-PpaHits@100: 48.63 -> 49.13Improved
consider multi-hop overlapped neighbors (L>1) instead of L=1 (ablation)Neo-GNN · OGB-CollabHits@50Improved
decrease decay factor beta (ablation)Neo-GNN · OGB-CollabHits@50No clear effect
use Neo-GNN structural features instead of feature-based GCNlink prediction · OGB-Citation2MRR: 84.79 -> 87.26Improved

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