Research map / Graph learning / GNN architectures
Neural Trees for Learning on Graphs
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 |
|---|---|---|---|
| Move GCN message passing from the input graph to the H-tree | GCN · 3D scene graphs test | accuracy: 40.88 ± 2.28 % -> 50.63 ± 2.25 % | Helped |
| Move GraphSAGE message passing from the input graph to the H-tree | GraphSAGE · 3D scene graphs test | accuracy: 59.54 ± 1.35 % -> 63.57 ± 1.54 % | Helped |
| Move GAT message passing from the input graph to the H-tree | GAT · 3D scene graphs test | accuracy: 46.56 ± 2.21 % -> 62.16 ± 2.03 % | Helped |
| Move GIN message passing from the input graph to the H-tree | GIN · 3D scene graphs test | accuracy: 49.25 ± 1.15 % -> 63.53 ± 1.38 % | Helped |
| Increase the treewidth bound used to sample the graph (ablation) | Neural Tree + GCN · Cora | test accuracy: about 2 percentage points | Helped |
| Increase the treewidth bound used to sample the graph (ablation) | Neural Tree + GCN · PubMed | test accuracy | No clear effect |
| Use more training nodes (ablation) | Neural Tree · 3D scene graphs | test accuracy | Helped |
| Use more training nodes (ablation) | Neural Tree · PubMed | test accuracy | Helped |
| Use more training nodes (ablation) | Neural Tree · CiteSeer and Cora | test accuracy | Mixed |
Closest papers by meaning
- TREE-G: Decision Trees Contesting Graph Neural Networks (AAAI 2024 · similarity 0.91)
- Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks (NeurIPS 2024 · similarity 0.89)
- On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.89)
- What do Graph Neural Networks learn? Insights from Tropical Geometry (NeurIPS 2024 · similarity 0.89)
- Improving Graph Neural Networks by Learning Continuous Edge Directions (ICLR 2025 · similarity 0.89)
- Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (ICML 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.