AI Paper Atlas

Research map / Graph learning / GNN architectures

Graph Information Bottleneck

Tailin Wu, Hongyu Ren, Pan Li, Jure Leskovec

NeurIPS 2020 · Graph learning › GNN architectures · approach: Graph structure learning · 105 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 GIB objective to GATGAT · Cora Nettackaccuracy: average +8.9%Improved
add GIB objective to GATGAT · Pubmed Nettackaccuracy: average +14.4%Improved
add GIB objective to GATGAT · Citeseer Nettack poisoningaccuracy: 38.0 -> 35.0Hurt
add GIB objectiveGAT · Pubmed cleanaccuracy: 78.6 -> 85.1Improved
add GIB objectiveGAT · Cora cleanaccuracy: 77.8 -> 77.6No clear effect
add feature IB (XIB) to structure IB (ablation)AIB-Cat · Cora Nettackaccuracy: 0.9% averageImproved
add structure IB (AIB) to feature IB (ablation)XIB · Cora Nettack evasive 1accuracy: 57.0 -> 63.0Improved
add feature IB to structure IB (ablation)AIB-Cat · Pubmed feature noise 1.5F1-micro: 43.0 -> 51.5Improved
add feature IB to structure IB (ablation)AIB-Bern · Citeseer feature noise 1.5F1-micro: 36.3 -> 46.1Improved

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