Research map / Graph learning / GNN architectures
Long Range Graph Benchmark
Vijay Prakash Dwivedi, Ladislav Rampášek, Mikhail Galkin, Ali Parviz, Guy Wolf, Anh Tuan Luu, Dominique Beaini
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 fully connected Transformer+LapPE instead of GatedGCN | Graph model · Peptides-struct test | MAE: 0.3420 -> 0.2529 | Improved |
| use SAN+RWSE instead of GatedGCN+RWSE | Graph model · Peptides-func test | AP: 0.6069 -> 0.6439 | Improved |
| use SAN+LapPE instead of GCN | Graph model · PCQM-Contact test | MRR: 0.3234 -> 0.3350 | Improved |
| use Transformer+LapPE instead of GatedGCN | Graph model · COCO-SP test | macro F1: 0.2641 -> 0.2618 | No clear effect |
| add LapPE/RWSE positional encoding to GatedGCN (ablation) | GatedGCN · PascalVOC-SP / Peptides | test metrics: 0.2873 -> 0.2860 (PascalVOC-SP F1) | No clear effect |
| use 2-layer MP-GNNs instead of 5-8 layers (ablation) | MP-GNNs · LRGB datasets | test performance | Hurt |
| use GCN/GINE simple aggregation vs GatedGCN (ablation) | local MP-GNN · PascalVOC-SP test | macro F1: 0.1268 -> 0.2873 (GCN to GatedGCN) | Hurt |
Closest papers by meaning
- On Measuring Long-Range Interactions in Graph Neural Networks (ICML 2025 · similarity 0.91)
- Learning Long Range Dependencies on Graphs via Random Walks (ICLR 2025 · similarity 0.90)
- Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (ICML 2025 · similarity 0.90)
- Recurrent Distance Filtering for Graph Representation Learning (ICML 2024 · similarity 0.89)
- Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks (NeurIPS 2025 · similarity 0.89)
- Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing (NeurIPS 2026 · 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.
