Research map / Graph learning / Graph self-supervised learning
GALA: Graph Diffusion-Based Alignment With Jigsaw for Source-Free Domain Adaptation
Junyu Luo, Yiyang Gu, Xiao Luo, Wei Ju, Zhiping Xiao, Yusheng Zhao, Jingyang Yuan, Ming Zhang
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 graph diffusion model alignment (ablation) | GALA · Average over six datasets (ablation) | accuracy (%): 54.7 -> 56.3 | Improved |
| add unbiased pseudo-labeling with curriculum learning (ablation) | GALA · Average over six datasets (ablation) | accuracy (%): 55.0 -> 56.3 | Improved |
| add consistency learning with graph jigsaw (ablation) | GALA · Average over six datasets (ablation) | accuracy (%): 55.5 -> 56.3 | Improved |
| add graph diffusion model alignment (ablation) | GALA · ENZYMES (ablation) | accuracy (%): 27.7 -> 30.7 | Improved |
| add unbiased pseudo-labeling with curriculum learning (ablation) | GALA · ENZYMES (ablation) | accuracy (%): 28.3 -> 30.7 | Improved |
| use GALA instead of PLUE | PLUE · COX2 and BZR source-free (avg over 4 tasks) | accuracy (%): 55.2 -> 60.5 | Improved |
| use GALA instead of PLUE | PLUE · ENZYMES source-free (avg over 12 density-split tasks) | accuracy (%): 26.1 -> 30.7 | Improved |
| use semi-supervised InfoGraph instead of source-only GCN | GCN · PROTEINS source-free (avg over 12 density-split tasks) | accuracy (%): 58.6 -> 59.4 | Mixed |
| raise initial pseudo-label threshold from 0.95 to 0.99 (ablation) | GALA · average accuracy sensitivity | accuracy (%) | Hurt |
| increase reconstruction timestamp t_recon beyond 0.1 (0.2 to 0.4) (ablation) | GALA · average accuracy sensitivity | accuracy (%) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InfoGraph — InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (ICLR 2020) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Rethinking Propagation for Unsupervised Graph Domain Adaptation (AAAI 2024 · similarity 0.89)
- Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation (NeurIPS 2024 · similarity 0.89)
- On the Benefits of Attribute-Driven Graph Domain Adaptation (ICLR 2025 · similarity 0.88)
- Open-Set Graph Domain Adaptation via Separate Domain Alignment (AAAI 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 0.87)
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.
