AI Paper Atlas

Research map / Graph learning / GNN architectures

Subgroup Generalization and Fairness of Graph Neural Networks

Jiaqi Ma, Junwei Deng, Qiaozhu Mei

NeurIPS 2021 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 24 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
Evaluate test nodes in subgroups with increasing aggregated-feature distance from the training setGCN, GAT, SGC, and APPNP · Cora, Citeseer, and Pubmedtest accuracyMixed
Evaluate test nodes in subgroups with increasing shortest-path distance from the training setGNN models · Cora, Citeseer, and Pubmedtest accuracyImproved
Group test nodes by centrality rather than distance to the training setGNN models · Cora, Citeseer, and Pubmedtest accuracyNo clear effect
Evaluate MLP test nodes in subgroups with increasing aggregated-feature or geodesic distance from training nodesMLP · Cora, Citeseer, and Pubmedtest accuracyMixed
Add independent noise to node features to reduce feature homophily (ablation)MLP · Cora, Citeseer, and Pubmedtest accuracy across aggregated-feature-distance subgroupsMixed
Add independent noise to node features to reduce feature homophily (ablation)GCN, GAT, SGC, and APPNP · Cora, Citeseer, and Pubmedtest accuracy across aggregated-feature-distance subgroupsNo clear effect
Select training nodes with high centrality for one dominant class and low centrality for other classes (ablation)GNN models · Cora, Citeseer, and Pubmedfalse positive rate for the dominant classHurt

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