DiffGDA uses diffusion and SDEs to model continuous structure-semantic evolution from source to target graphs. A domain-aware network guides trajectories to optimal adaptation paths. Outperforms baselines on 14 tasks across 8 datasets.
Key Points
- 1.Continuous-time generative process via SDEs
- 2.Joint structural and semantic modeling
- 3.Theoretical convergence to optimal latent bridge
Impact Analysis
Advances GDA for real-world nonlinear graph shifts, improving transfer from labeled sources to unlabeled targets.
Technical Details
Formulates adaptation as diffusion trajectories steered by domain network; tested on diverse graph benchmarks.