Research map / Graph learning / Graph self-supervised learning
Progressive Graph Structure Adjustment for Homophily Shift Adaptation
Hongwei Wen, Can Zhang, Haoyu He, Hanyuan Hang, Minglong Lei
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 source-side and target-side structure adjustment (ablation) | PSAHS · Blog B1-B2 | accuracy: 54.30 -> 88.05 | Improved |
| add source-side and target-side structure adjustment (ablation) | PSAHS · Blog B2-B1 | accuracy: 56.25 -> 89.64 | Improved |
| add source-side structure adjustment to target-only adjustment (ablation) | PSAHS · Blog B1-B2 | accuracy: 82.10 -> 88.05 | Improved |
| add target-side structure adjustment to source-only adjustment (ablation) | PSAHS · Blog B1-B2 | accuracy: 61.66 -> 88.05 | Improved |
| add target-side adjustment to source-only adjustment (ablation) | PSAHS · Blog B2-B1 | accuracy: 60.17 -> 89.64 | Improved |
| add source-side adjustment to target-only adjustment (ablation) | PSAHS · Airport B-E | accuracy: 55.58 -> 60.03 | Improved |
| add target-side adjustment to source-only adjustment (ablation) | PSAHS · Airport B-E | accuracy: 54.34 -> 60.03 | Improved |
| add structure adjustment in both domains (ablation) | PSAHS · Airport U-E | accuracy: 49.33 -> 59.20 | Improved |
| add structure adjustment in both domains (ablation) | PSAHS · Airport E-B | accuracy: 67.54 -> 74.34 | Improved |
| use GNN-MLP agreement pseudo-labels instead of all GNN pseudo-labels (ablation) | PSAHS · Blog B1-B2 | accuracy: 0.54 -> 0.88 | Improved |
| use GNN-MLP agreement pseudo-labels instead of MLP pseudo-labels (ablation) | PSAHS · Blog B1-B2 | accuracy: 0.76 -> 0.88 | Improved |
| use GNN-MLP agreement pseudo-labels instead of prototype pseudo-labels (ablation) | PSAHS · Blog B1-B2 | accuracy: 0.60 -> 0.88 | Improved |
Closest papers by meaning
- Homophily Enhanced Graph Domain Adaptation (ICML 2025 · similarity 0.92)
- Pairwise Alignment Improves Graph Domain Adaptation (ICML 2024 · similarity 0.89)
- Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation (AAAI 2025 · similarity 0.88)
- DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation (NeurIPS 2026 · similarity 0.88)
- On the Benefits of Attribute-Driven Graph Domain Adaptation (ICLR 2025 · similarity 0.88)
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 2025 · 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.
