Research map / Label-efficient and robust learning / Domain adaptation and generalization
GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation
Check 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 |
|---|---|---|---|
| jointly model data structure, domain labels, and class labels with structure-aware, domain, and class-centroid alignment | GCAN with AlexNet · Office-31 (six transfer tasks) | mean accuracy (%): 79.1 -> 80.6 | Helped |
| jointly model data structure, domain labels, and class labels with structure-aware, domain, and class-centroid alignment | GCAN with AlexNet · ImageCLEF-DA (six transfer tasks) | mean accuracy (%): 80.0 -> 80.9 | Helped |
| jointly model data structure, domain labels, and class labels with structure-aware, domain, and class-centroid alignment | GCAN with AlexNet · Office-Home (12 transfer tasks) | mean accuracy (%): 48.46 -> 51.05 | Helped |
| jointly model data structure, domain labels, and class labels with three alignment mechanisms | GCAN with AlexNet · Office-31 A → W | accuracy (%): 80.5±0.4 -> 82.7±0.1 | Helped |
| jointly model data structure, domain labels, and class labels with three alignment mechanisms | GCAN with AlexNet · Office-31 D → W | accuracy (%): 96.9±0.1 -> 97.1±0.1 | Helped |
| jointly model data structure, domain labels, and class labels with three alignment mechanisms | GCAN with AlexNet · Office-31 W → D | accuracy (%): 99.9±0.1 -> 99.8±0.1 | Hurt |
| jointly model data structure, domain labels, and class labels with three alignment mechanisms | GCAN with AlexNet · Office-31 A → D | accuracy (%): 74.5±0.4 -> 76.4±0.5 | Helped |
| jointly model data structure, domain labels, and class labels with three alignment mechanisms | GCAN with AlexNet · Office-31 D → A | accuracy (%): 62.5±0.4 -> 64.9±0.1 | Helped |
| jointly model data structure, domain labels, and class labels with three alignment mechanisms | GCAN with AlexNet · Office-31 W → A | accuracy (%): 60.0±0.6 -> 62.6±0.3 | Helped |
Closest papers by meaning
- Graph-Relational Domain Adaptation (ICLR 2022 · similarity 0.90)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.90)
- Rethinking Propagation for Unsupervised Graph Domain Adaptation (AAAI 2024 · similarity 0.90)
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation (NeurIPS 2024 · similarity 0.89)
- Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain Alignment (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.