Research map / Graph learning / GNN architectures
Hyperbolic Graph Convolutional Neural 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 trainable curvature, attention-based hyperbolic aggregation, and Lorentz-manifold optimization (ablation) | Hyperbolic GCN · Graph prediction tasks | Predictive accuracy: up to $9.9\%$ absolute gain | Helped |
| Aggregate in each point's local tangent space rather than the tangent space at the origin (ablation) | HGCN · Graph prediction tasks | Predictive performance | Helped |
| Compute attention scores from the origin (ablation) | HGCN · Graph prediction tasks | Predictive performance | Helped |
| Use the hyperboloid model instead of the Poincare model | Hyperbolic GCN · Graph prediction tasks | Optimization stability | Helped |
Closest papers by meaning
- A Hyperbolic-to-Hyperbolic Graph Convolutional Network (CVPR 2021 · similarity 0.94)
- Residual Hyperbolic Graph Convolution Networks (AAAI 2024 · similarity 0.94)
- Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach (NeurIPS 2023 · similarity 0.93)
- Fully Hyperbolic Convolutional Neural Networks for Computer Vision (ICLR 2024 · similarity 0.90)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.89)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.89)
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.