Domain-Adapted Diffusion Models for Conditional Independence Testing
Domain-Adapted Diffusion (DA-Diff), a multi-source domain adaptation framework for conditional diffusion models based on weighted empirical risk minimization over both target and source domains, is proposed andExperiments demonstrate that DA-Diff improved conditional generation quality compared with transfer-learning d...
Yan-Feng Yang, Jun-Da Zhao, Yi-Jie Gao et al.
· 0 citations