Research map / Graph learning / Graph self-supervised learning
Cross-Domain Few-Shot Graph Classification
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 |
|---|---|---|---|
| Add the multi-view encoder to metric-based meta-learning | MatchNet, ProtoNet, and RelationNet · Molecules, Bioinformatics, and Social Networks | 1-shot accuracy: +3.28%, +4.29%, and +5.17% absolute accuracy | Helped |
| Add node-degree encodings to contextual features (ablation) | MatchNet · Molecules | 1-shot accuracy: 58.89 ± 6.31 -> 60.15 ± 6.35 | Helped |
| Add diffusion eigenvalue representation to contextual features (ablation) | MatchNet · Molecules | 1-shot accuracy: 58.89 ± 6.31 -> 61.47 ± 7.82 | Helped |
| Use both topological views alongside contextual features (ablation) | MatchNet · Molecules | 1-shot accuracy: 58.89 ± 6.31 -> 62.17 ± 6.14 | Helped |
| Use both topological views alongside contextual features (ablation) | MatchNet · Bioinformatics | 1-shot accuracy: 54.83 ± 7.66 -> 59.12 ± 7.00 | Helped |
| Use both topological views alongside contextual features (ablation) | MatchNet · Social Networks | 1-shot accuracy: 62.25 ± 9.14 -> 67.42 ± 10.37 | Helped |
| Condition the attention module on stored task encodings and similar-task encodings (ablation) | Proposed encoder · Cross-domain graph classification | accuracy | No clear effect |
| Use simple feature padding instead of heterogeneous feature augmentation or Deep Sets (ablation) | Contextual-view augmentation · Cross-domain graph classification | accuracy | Helped |
| Use graph diffusion rather than heat kernel, normalized Laplacian eigenvalues, or shortest-path matrix (ablation) | Topological structural view · Cross-domain graph classification | accuracy | Helped |
| Use mean pooling rather than attention pooling, jumping knowledge, or summation pooling (ablation) | Graph-view encoder · Cross-domain graph classification | accuracy | No clear effect |
Closest papers by meaning
- When Sparse Graph Representation Learning Falls into Domain Shift: Data Augmentation for Cross-Domain Graph Meta-Learning (Student Abstract) (AAAI 2024 · similarity 0.88)
- Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration (NeurIPS 2025 · similarity 0.88)
- UniGTE: Unified Graph–Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains (NeurIPS 2025 · similarity 0.87)
- Open-Set Graph Domain Adaptation via Separate Domain Alignment (AAAI 2024 · similarity 0.87)
- Unlocking the Potential of Black-box Pre-trained GNNs for Graph Few-shot Learning (AAAI 2025 · similarity 0.86)
- Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs (AAAI 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.