Research map / Graph learning / GNN architectures
Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
Lu Bai, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock
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 |
|---|---|---|---|
| add backtrackless grid construction (BASGCN vs BASGCN(U)) (ablation) | BASGCN · MUTAG | accuracy (%): 89.70 -> 90.04 | Improved |
| add backtrackless grid construction (ablation) | BASGCN · D&D | accuracy (%): 80.40 -> 81.20 | Improved |
| add backtrackless grid construction (ablation) | BASGCN · RED-B | accuracy (%): 90.60 -> 91.00 | Improved |
| add backtrackless grid construction (ablation) | BASGCN · COLLAB | accuracy (%): 78.75 -> 79.60 | Improved |
| add backtrackless grid construction (ablation) | BASGCN · IMDB-B | accuracy (%): 73.86 -> 74.00 | Improved |
| add backtrackless grid construction (ablation) | BASGCN · PROTEINS | accuracy (%): 76.50 -> 76.05 | Hurt |
| add backtrackless grid construction (ablation) | BASGCN · PTC | accuracy (%): 61.42 -> 60.50 | Hurt |
| add backtrackless grid construction (ablation) | BASGCN · IMDB-M | accuracy (%): 50.86 -> 50.43 | Hurt |
| use BASGCN instead of JTQK graph kernel | JTQK · RED-B | accuracy (%): 77.60 -> 91.00 | Improved |
| use BASGCN instead of JTQK graph kernel | JTQK · MUTAG | accuracy (%): 85.50 -> 90.04 | Improved |
| use BASGCN instead of DGCNN | DGCNN · COLLAB | accuracy (%): 73.76 -> 79.60 | Improved |
| use BASGCN instead of DGCNN | DGCNN · IMDB-B | accuracy (%): 70.03 -> 74.00 | Improved |
Closest papers by meaning
- Learning Convolutional Neural Networks for Graphs (ICML 2016 · similarity 0.90)
- Simplifying Graph Convolutional Networks (ICML 2019 · similarity 0.89)
- Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning (AAAI 2018 · similarity 0.89)
- Beyond Graph Convolutional Network: An Interpretable Regularizer-Centered Optimization Framework (AAAI 2023 · similarity 0.89)
- pathGCN: Learning General Graph Spatial Operators from Paths (ICML 2022 · similarity 0.89)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.88)
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.
