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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use hyperbolic instead of diffusion dynamics (ablation) | PDE-GCN · Cora semi-supervised (32 layers) | accuracy: 83.9 -> 77.8 | Hurt |
| use hyperbolic instead of diffusion dynamics (ablation) | PDE-GCN · CiteSeer (32 layers) | accuracy: 75.6 -> 72.5 | Hurt |
| use hyperbolic instead of diffusion dynamics | PDE-GCN · FAUST | % zero geodesic error: 64.2 -> 99.9 | Improved |
| remove K^T so operator is non-symmetric (not positive semi-definite) (ablation) | PDE-GCN_D · CiteSeer (32 layers) | accuracy: 75.6 -> 73.9 | Hurt |
| use ReLU instead of tanh (ablation) | PDE-GCN_D · CiteSeer (32 layers) | accuracy: 75.6 -> 73.6 | Hurt |
| learn mixture of diffusion and hyperbolic dynamics | PDE-GCN_M vs PDE_D · Texas fully-supervised | accuracy: 90.81 -> 93.24 | Improved |
| learn mixture of diffusion and hyperbolic dynamics (ablation) | PDE-GCN_M vs PDE_D · CiteSeer semi-supervised (32 layers) | accuracy: 75.6 -> 75.4 | No clear effect |
| increase depth from 2 to 32 layers | PDE-GCN_D · CiteSeer semi-supervised | accuracy: 74.6 -> 75.6 | Improved |
| add diffusion update to DGCNN (ablation) | DGCNN · Cora (2 layers) | accuracy: 34.9 -> 71.0 | Improved |
| PDE-GCN_D vs GCNII on PPI | PDE-GCN_D · PPI | micro-F1: 99.58 -> 99.07 | Hurt |
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.
- SplineCNN — SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline Kernels (CVPR 2018) · better on 1 of 1 shared result
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
- Graph Neural PDE Solvers with Conservation and Similarity-Equivariance (ICML 2024 · similarity 0.91)
- Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations (ICML 2025 · similarity 0.91)
- PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems (ICLR 2025 · similarity 0.87)
- Mechanistic PDE Networks for Discovery of Governing Equations (ICML 2025 · similarity 0.87)
- SNN-PDE: Learning Dynamic PDEs from Data with Simplicial Neural Networks (AAAI 2024 · similarity 0.85)
- HAMLET: Graph Transformer Neural Operator for Partial Differential Equations (ICML 2024 · similarity 0.85)
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.
