Research map / Label-efficient and robust learning / Domain adaptation and generalization
Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning
Yingxu Wang, Mengzhu Wang, Zhichao Huang, Suyu Liu, Nan Yin
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 implicit branch (GMT) to the dual-branch model (ablation) | NeGPR · PROTEINS P0→P1 | accuracy (%): 50.8 -> 71.7 | Improved |
| add explicit branch (PathNN) to the dual-branch model (ablation) | NeGPR · PROTEINS P0→P1 | accuracy (%): 50.4 -> 71.7 | Improved |
| add noise-resilient neighborhood-consistency loss in pretraining (ablation) | NeGPR · PROTEINS P0→P3 | accuracy (%): 73.6 -> 77.1 | Improved |
| add noisy pseudo-label tolerated regularization in fine-tuning (ablation) | NeGPR · PROTEINS P0→P3 | accuracy (%): 74.8 -> 77.1 | Improved |
| raise pseudo-label confidence threshold from 0.5 to 0.9 (ablation) | NeGPR · PROTEINS | accuracy | Improved |
| increase source label noise ratio from 0.1 to 0.5 (ablation) | NeGPR · PROTEINS | accuracy | Hurt |
| use GMT for IB and PathNN for EB instead of other backbones (ablation) | NeGPR · PROTEINS | accuracy | Improved |
| NeGPR vs best baseline ALEX on P1→P0 | NeGPR · PROTEINS P1→P0 | accuracy (%): 74.9 -> 74.7 | No clear effect |
Closest papers by meaning
- Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation (NeurIPS 2024 · similarity 0.90)
- Pairwise Alignment Improves Graph Domain Adaptation (ICML 2024 · similarity 0.89)
- Open-Set Graph Domain Adaptation via Separate Domain Alignment (AAAI 2024 · similarity 0.89)
- TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering (NeurIPS 2024 · similarity 0.88)
- Homophily Enhanced Graph Domain Adaptation (ICML 2025 · similarity 0.88)
- Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation (AAAI 2025 · 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.
