AI Paper Atlas

Research map / Graph learning / GNN architectures

Neural Structured Prediction for Inductive Node Classification

Meng Qu, Huiyu Cai, Jian Tang

ICLR 2022 · Graph learning › GNN architectures · approach: GNN generalization theory · 2 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 SPN-GraphSAGE instead of GraphSAGEPPI-1 · PPI-1accuracy (%): 81.02 ± 0.07 -> 82.11 ± 0.03Improved
Use SPN-GraphSAGE instead of GraphSAGEPPI-1 · PPI-1micro-F1 (%): 67.30 ± 0.11 -> 68.56 ± 0.07Improved
Use SPN-GCNII instead of GCNIIPPI-2 · PPI-2accuracy (%): 84.81 ± 0.06 -> 85.83 ± 0.04Improved
Use SPN-GCNII instead of GCNIIPPI-2 · PPI-2micro-F1 (%): 74.54 ± 0.14 -> 75.96 ± 0.05Improved
Use SPN-GCNII instead of GCNIIPPI-10 · PPI-10accuracy (%): 97.53 ± 0.01 -> 97.55 ± 0.01No clear effect
Use SPN-GCNII instead of GCNIIPPI-10 · PPI-10micro-F1 (%): 95.86 ± 0.01 -> 95.87 ± 0.02No clear effect
Use SPN-GCNII instead of GCNIIPPI · PPIaccuracy (%): 99.39 ± 0.00 -> 99.41 ± 0.00No clear effect
Use SPN-GCNII instead of GCNIIPPI · PPImicro-F1 (%): 98.97 ± 0.00 -> 99.02 ± 0.00No clear effect
Use SPN-GCNII instead of GCNIICora* · Cora*graph-level accuracy (%): 59.15 ± 0.67 -> 60.47 ± 0.49Improved
Use SPN-GAT instead of GMNNCiteseer* · Citeseer*graph-level accuracy (%): 48.46 ± 1.06 -> 49.02 ± 0.78No clear effect
Use SPN-GCNII instead of GCNIIPubmed* · Pubmed*graph-level accuracy (%): 53.54 ± 0.98 -> 54.35 ± 0.64Improved
Use SPN-GAT instead of GCNIIDBLP · DBLPaccuracy (%): 81.79 ± 0.88 -> 84.84 ± 0.73Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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