Research map / Graph learning / GNN architectures
Directional Graph Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add directional derivative aggregation to a mean-aggregation GNN (ablation) | DGN · ZINC, MolHIV, and MolPCBA | task performance | Helped |
| Use directional aggregators instead of mean aggregation (ablation) | Simple, complex, and complex-with-edges GNNs · CIFAR10, ZINC, PATTERN, MolHIV, and MolPCBA | task performance | Helped |
| Use the first two non-trivial Laplacian eigenvectors as positional encodings rather than directional flows (ablation) | Mean-aggregator GNN · Most benchmark datasets | task performance | No clear effect |
| Add random rotation or distortion of directional kernels (ablation) | DGN trained on reduced CIFAR10 · CIFAR10 training subset | test-set accuracy | Helped |
| Use excessively large rotation or distortion of directional kernels (ablation) | DGN trained on reduced CIFAR10 · CIFAR10 training subset | test-set accuracy | Hurt |
Closest papers by meaning
- Improving Graph Neural Networks by Learning Continuous Edge Directions (ICLR 2025 · similarity 0.89)
- A Manifold Perspective on the Statistical Generalization of Graph Neural Networks (ICML 2025 · similarity 0.88)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.87)
- Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes (AAAI 2024 · similarity 0.87)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.87)
- Spatio-Spectral Graph Neural Networks (NeurIPS 2024 · similarity 0.87)
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.