Research map / Graph learning / Graph self-supervised learning
Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation
Joonhyung Park, Hajin Shim, Eunho Yang
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 Graph Transplant instead of basic graph augmentation baselines | GNN graph classification · Multiple graph classification datasets | accuracy or AUROC | Improved |
| Add edge prediction to connect transplanted subgraphs (ablation) | Graph Transplant · Small graph classification datasets | classification performance | Improved |
| Use saliency-based rather than size-based label mixing (ablation) | Graph Transplant · Small graph classification datasets | classification performance | Improved |
| Use K-hop subgraphs instead of scattered nodes as mixing units (ablation) | Graph Transplant · Small graph classification datasets | classification performance | Improved |
| Select source subgraphs by node saliency instead of randomly (ablation) | Graph Transplant · Small graph classification datasets | classification performance | Improved |
| Use degree-preservation connectivity rather than edge prediction | Graph Transplant · Some graph classification datasets | classification performance | Mixed |
| Train with Graph Transplant rather than vanilla training | GNN · GradArgmax white-box attacks on ENZYMES, Mutagenicity, and NCI1 | accuracy | Improved |
| Train with Graph Transplant rather than vanilla training | GNN · ENZYMES, Mutagenicity, and COIL-DEL | Expected Calibration Error | Improved |
Closest papers by meaning
- AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification (AAAI 2025 · similarity 0.89)
- Graph Invariant Learning with Subgraph Co-mixup for Out-of-Distribution Generalization (AAAI 2024 · similarity 0.88)
- IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors (NeurIPS 2024 · similarity 0.87)
- Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classifications (AAAI 2025 · similarity 0.87)
- Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models (NeurIPS 2025 · similarity 0.87)
- Towards Pre-trained Graph Condensation via Optimal Transport (NeurIPS 2025 · similarity 0.86)
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.
