Research map / Graph learning / GNN architectures
Structural Landmarking and Interaction Modelling: A “SLIM” Network for Graph Classification
Yaokang Zhu, Kai Zhang, Jun Wang, Haibin Ling, Jie Zhang, Hongyuan Zha
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 |
|---|---|---|---|
| replace landmark density features with landmark interaction features (ablation) | SLIM · MUTAG | accuracy: 84.36 -> 93.28 | Improved |
| replace landmark density features with landmark interaction features (ablation) | SLIM · PTC | accuracy: 58.94 -> 74.41 | Improved |
| replace landmark density features with landmark interaction features (ablation) | SLIM · PROTEINS | accuracy: 71.25 -> 77.47 | Improved |
| replace landmark density features with landmark interaction features (ablation) | SLIM · NCI1 | accuracy: 68.34 -> 80.53 | Improved |
| use SLIM rather than the strongest listed baseline | graph classification · MUTAG | accuracy: 92.63±4.21 -> 93.28±3.36 | Improved |
| use SLIM rather than the strongest listed baseline | graph classification · PTC | accuracy: 71.46±2.21 -> 72.41±6.92 | Improved |
| use SLIM rather than the strongest listed baseline | graph classification · NCI1 | accuracy: 84.46±0.45 -> 80.53±2.01 | Hurt |
| use SLIM rather than the strongest listed baseline | graph classification · Protein | accuracy: 76.89±1.67 -> 77.47±4.34 | Improved |
| use SLIM rather than the strongest listed baseline | graph classification · D&D | accuracy: 79.72±1.98 -> 79.61±2.66 | Hurt |
| use SLIM rather than the strongest listed baseline | graph classification · IMDB-B | accuracy: 75.93±3.61 -> 77.23±2.12 | Improved |
| use SLIM rather than the strongest listed baseline | graph classification · IMDB-M | accuracy: 52.82±4.65 -> 53.38±4.02 | Improved |
| use SLIM rather than the strongest listed baseline | graph classification · COLLAB | accuracy: 83.60±1.22 -> 78.22±2.02 | Hurt |
Closest papers by meaning
- On the Ability of Graph Neural Networks to Model Interactions Between Vertices (NeurIPS 2023 · similarity 0.89)
- OpenGSL: A Comprehensive Benchmark for Graph Structure Learning (NeurIPS 2023 · similarity 0.89)
- The Underappreciated Power of Vision Models for Graph Structural Understanding (NeurIPS 2025 · similarity 0.87)
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 2025 · similarity 0.87)
- Explaining Graph Neural Networks via Structure-aware Interaction Index (ICML 2024 · similarity 0.87)
- Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval (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.
