AI Paper Atlas

Research map / Graph learning / GNN architectures

Path Neural Networks: Expressive and Accurate Graph Neural Networks

Gaspard Michel, Giannis Nikolentzos, Johannes F. Lutzeyer, Michalis Vazirgiannis

ICML 2023 · Graph learning › GNN architectures · approach: Subgraph and distance-aware GNNs · 4 citations (OpenAlex)

Read the paper

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 PathNN-SP+ instead of 3WLGNNgraph classification · CSLaccuracy: 97.8 ± 10.9 -> 100.0 ± 0.0Improved
use PathNN-SP instead of 3WLGNNgraph classification · CSLaccuracy: 97.8 ± 10.9 -> 90.0 ± 0.0Hurt
aggregate all simple paths instead of single shortest paths (ablation)PathNN · CSLaccuracy: 90.0 ± 0.0 -> 100.0 ± 0.0Improved
use PathNN-SP+ instead of GINgraph classification · NCI1accuracy: 80.0 ± 1.4 -> 82.3 ± 1.9Improved
increase path length from K=1 to K=3 (ablation)PathNN-SP · NCI1accuracy: 77.5 ± 1.6 -> 82.2 ± 1.7Improved
increase path length from K=1 to K=3 (ablation)PathNN-SP · DDaccuracy: 76.9 ± 3.7 -> 77.0 ± 3.1No clear effect
use PathNN-P (K=1) instead of the strongest listed baselinegraph classification · ENZYMESaccuracy: 69.4 ± 6.2 -> 73.0 ± 5.2Improved
use PathNN-P (K=1) instead of GINgraph classification · IMDB-Maccuracy: 48.5 ± 3.3 -> 50.8 ± 4.5Improved
use PathNN-SP instead of GCNgraph classification · Peptides-FunctionalAverage Precision: 59.30 ± 0.23 -> 68.16 ± 0.26Improved
use PathNN-SP+ instead of GatedGCNgraph regression · Peptides-StructuralMean Absolute Error: 0.3420 ± 0.0013 -> 0.2540 ± 0.0046Improved
use PathNN-SP+ instead of CINgraph classification · ogbg-molhivROC-AUC: 80.94 ± 0.57 -> 79.17 ± 1.09Hurt
use PathNN-AP instead of CINgraph regression · ZINC12KMean Absolute Error: 0.079 ± 0.006 -> 0.090 ± 0.004Hurt

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