AI Paper Atlas

Research map / Graph learning / GNN architectures

PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations

Moshe Eliasof, Eldad Haber, Eran Treister

NeurIPS 2021 · Graph learning › GNN architectures · approach: Oversmoothing and heterophily · 18 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 hyperbolic instead of diffusion dynamics (ablation)PDE-GCN · Cora semi-supervised (32 layers)accuracy: 83.9 -> 77.8Hurt
use hyperbolic instead of diffusion dynamics (ablation)PDE-GCN · CiteSeer (32 layers)accuracy: 75.6 -> 72.5Hurt
use hyperbolic instead of diffusion dynamicsPDE-GCN · FAUST% zero geodesic error: 64.2 -> 99.9Improved
remove K^T so operator is non-symmetric (not positive semi-definite) (ablation)PDE-GCN_D · CiteSeer (32 layers)accuracy: 75.6 -> 73.9Hurt
use ReLU instead of tanh (ablation)PDE-GCN_D · CiteSeer (32 layers)accuracy: 75.6 -> 73.6Hurt
learn mixture of diffusion and hyperbolic dynamicsPDE-GCN_M vs PDE_D · Texas fully-supervisedaccuracy: 90.81 -> 93.24Improved
learn mixture of diffusion and hyperbolic dynamics (ablation)PDE-GCN_M vs PDE_D · CiteSeer semi-supervised (32 layers)accuracy: 75.6 -> 75.4No clear effect
increase depth from 2 to 32 layersPDE-GCN_D · CiteSeer semi-supervisedaccuracy: 74.6 -> 75.6Improved
add diffusion update to DGCNN (ablation)DGCNN · Cora (2 layers)accuracy: 34.9 -> 71.0Improved
PDE-GCN_D vs GCNII on PPIPDE-GCN_D · PPImicro-F1: 99.58 -> 99.07Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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