AI Paper Atlas

Research map / Graph learning / GNN architectures

Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs

Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang

ICLR 2023 · Graph learning › GNN architectures · approach: Subgraph and distance-aware GNNs · 3 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 an identifier for each neighbor of the root nodeSubgraph MPNNs, forming I^2-GNN · SR25accuracy: 0% -> 100%Improved
Add an identifier for each neighbor of the root nodeSubgraph MPNNs, forming I^2-GNN · Syntheticnormalized MAE, 5-Cycle: 0.0402 -> 0.0028Improved
Add an identifier for each neighbor of the root nodeSubgraph MPNNs, forming I^2-GNN · Syntheticnormalized MAE, 6-Cycle: 0.0439 -> 0.0082Improved
Add an identifier for each neighbor of the root nodeSubgraph MPNNs, forming I^2-GNN · ChEMBLnormalized MAE, 6-Cycle: 0.0053 -> 0.0003Improved
Add an identifier for each neighbor of the root nodeSubgraph MPNNs, forming I^2-GNN · Syntheticnormalized MAE, 4-Cycle: 0.0009 -> 0.0016Mixed
Use I^2-GNN instead of NGNNMolecular property prediction · QM9MAE across targets: 21.6% improvementImproved
Use I^2-GNN instead of Nested GINMolecular graph regression · ZINC-12KMAE: 25% performance gainsImproved
Use I^2-GNN instead of Nested GINMolecular graph regression · ZINC-250KMAE: 18% performance gainsImproved
Use I^2-GNN instead of Nested GINMolecular graph classification · ogbg-molhivAUC: 0.3%Improved
Use I^2-GNN instead of CINMolecular graph classification · ogbg-molhivAUC: $80.94\!\pm\!0.57$ -> $78.68\!\pm\!0.93$Hurt

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