AI Paper Atlas

Research map / Graph learning / GNN architectures

Graph Neural Networks with Adaptive Residual

Xiaorui Liu, Jiayuan Ding, Wei Jin, Han Xu, Yao Ma, Zitao Liu, Jiliang Tang

NeurIPS 2021 · Graph learning › GNN architectures · approach: Structural GNN variants · 20 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 residual connections to message passing (APPNP, GCNII, GCN) (ablation)GNNs with abnormal node features · Cora/CiteSeer/PubMed with 10% Gaussian-noise nodesaccuracy on abnormal nodesHurt
add residual connections to message passing (ablation)GNNs with abnormal node features · Cora/CiteSeer/PubMedaccuracy on normal nodes with more layersImproved
increase number of feature aggregation layers without residual (ablation)GNNs · Cora/CiteSeer/PubMedaccuracyMixed
use AirGNN adaptive residual instead of GAT/GCN/GCNII/APPNPsemi-supervised node classification · Cora, CiteSeer, PubMed noisy featuresaccuracy on noisy nodesImproved
use AirGNN instead of baselinesnode classification under Nettack feature attack · Cora, CiteSeer, PubMed adversarial featuresaccuracy on attacked nodesImproved
use AirGNN instead of baselinesnode classification with noisy nodes present · Cora, CiteSeer, PubMedaccuracy on normal nodesImproved
adaptive per-node residual weight (1-beta) for abnormal vs normal nodes (ablation)AirGNN · Cora noisy featuresaverage residual weight: 0.076 -> 0.002 (normal vs abnormal nodes)Improved

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