AI Paper Atlas

Research map / Graph learning / GNN architectures

Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

Oleg Platonov, Denis Kuznedelev, Artem Babenko, Liudmila Prokhorenkova

NeurIPS 2023 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 9 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 label informativeness (LI) instead of adjusted homophily to explain GNN accuracyGraphSAGE · synthetic SBM graphsSpearman correlation with accuracy: 0.05 -> 0.93Improved
use LI instead of adjusted homophily to explain GNN accuracyGCN · synthetic SBM graphsSpearman correlation with accuracy: 0.19 -> 0.76Improved
use LI instead of adjusted homophily to explain GNN accuracyGAT · synthetic SBM graphsSpearman correlation with accuracy: 0.17 -> 0.77Improved
use LI instead of homophily measures to explain GNN accuracyGCN · semi-synthetic coraSpearman correlation with accuracy: -0.31 -> 0.72Improved
use LI instead of homophily measures to explain GNN accuracyGraphSAGE · semi-synthetic citeseerSpearman correlation with accuracy: -0.54 -> 0.51Improved
use adjusted homophily instead of edge homophily to characterize binary datasetsquestions dataset · questionshomophily value: 0.84 -> 0.02Mixed

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