Research map / Graph learning / Graph self-supervised learning
SAGA: Structural Aggregation Guided Alignment with Dynamic View and Neighborhood Order Selection for Multiview Graph Domain Adaptation
Ruiyi Fang, Jingyu Zhao, Shuo Wang, Ruizhi Pu, Bingheng Li, Jiale Cai, Zhihao Li, Zihao Jing, Jian Zhu, Song Tang, Charles Ling, Boyu Wang
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 |
|---|---|---|---|
| Use all views jointly instead of best single view (ablation) | SAGA · ACM1->ACM2 | accuracy: 0.379 -> 0.523 | Improved |
| Use all views jointly instead of best single view (ablation) | SAGA · ACM1->ACM2 | macro-F1: 0.339 -> 0.351 | Improved |
| Use all views jointly instead of best single view (ablation) | SAGA · ACM2->ACM1 | accuracy: 0.389 -> 0.454 | Improved |
| Use all views jointly instead of best single view (ablation) | SAGA · MAG CN->US | accuracy: 0.335 -> 0.553 | Improved |
| Use all views jointly instead of best single view (ablation) | SAGA · MAG US->CN | accuracy: 0.349 -> 0.535 | Improved |
| Use all views jointly instead of best single view (ablation) | SAGA · MAG CN->US | macro-F1: 0.230 -> 0.341 | Improved |
| Add Dominant View Alignment module (versus DANN alignment) (ablation) | SAGA · ACM1/ACM2 | accuracy | Improved |
| Add dynamic hop selection instead of fixed hop number (ablation) | SAGA · ACM1/ACM2 | accuracy | Improved |
| Add dominant view selection instead of simple view averaging (ablation) | SAGA · ACM1/ACM2 | accuracy | Improved |
| Use SAGA instead of HGDA | HGDA baseline · ACM1->ACM2 | accuracy: 0.511 -> 0.523 | Improved |
| Use SAGA instead of HGDA | HGDA baseline · MAG CN->US | accuracy: 0.417 -> 0.553 | Improved |
| Use SAGA instead of PA | PA baseline · ACM2->ACM1 | macro-F1: 0.377 -> 0.444 | Improved |
Closest papers by meaning
- Pairwise Alignment Improves Graph Domain Adaptation (ICML 2024 · similarity 0.90)
- Homophily Enhanced Graph Domain Adaptation (ICML 2025 · similarity 0.90)
- On the Benefits of Attribute-Driven Graph Domain Adaptation (ICLR 2025 · similarity 0.89)
- TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering (NeurIPS 2024 · similarity 0.88)
- Open-Set Graph Domain Adaptation via Separate Domain Alignment (AAAI 2024 · similarity 0.88)
- Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation (NeurIPS 2024 · 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.
