AI Paper Atlas

Research map / Graph learning / GNN architectures

Affinity-Aware Graph Networks

Ameya Velingker, Ali Kemal Sinop, Ira Ktena, Petar Veličković, Sreenivas Gollapudi

NeurIPS 2023 · Graph learning › GNN architectures · approach: Expressive equivariant message passing · 1 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 effective-resistance edge features to MPNNMPNN · PNA test avglog(MSE): -2.665 -> -2.779Improved
use hitting times instead of effective resistance as edge featuresER GNN · PNA test avglog(MSE): -2.779 -> -2.816Improved
combine all ER features (ER, HT, node and edge embeddings)ER GNN · PNA test avglog(MSE): -2.779 -> -3.106Improved
add random node features to MPNNMPNN · PNA test avglog(MSE): -2.665 -> -2.490Hurt
apply random rotations to ER node embeddings (ablation)MPNN + ER node embeddings · ogbg-molhivROC-AUC: 77.77 -> 76.28Hurt
apply random rotations to ER node embeddings + HT (ablation)MPNN + ER node embeddings + HT · ogbg-molhivROC-AUC: 78.16 -> 79.13Improved
add hitting times to ER node embeddings (ablation)MPNN + ER node embeddings · ogbg-molhivROC-AUC: 77.77 -> 78.16Improved
add random features to MPNN (ablation)MPNN · ogbg-molpcba (4 layers)mAP: 27.75 -> 26.69Hurt
add ER features to MPNN + Noisy Nodes at 4 layersMPNN + Noisy Nodes · ogbg-molpcba (4 layers)mAP: 27.92 -> 28.11Improved
add ER features to MPNN + Noisy Nodes at 16 layersMPNN + Noisy Nodes · ogbg-molpcba (16 layers)mAP: 28.29 -> 28.28No clear effect
add ER scalar features to GATGAT · ogbn-arXivaccuracy: 72.02 -> 72.14Improved
add hitting time features to GATGAT · ogbn-arXivaccuracy: 72.14 -> 72.25Improved

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