SPIRE adds per-client embeddings to a shared diffusion backbone, enabling parameter-efficient personalization in federated learning, with new-client KID improvements on MNIST, CIFAR-10, and CelebA.
Ten steps of em suffice for mixtures of two gaussians
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SPIRE: Conditional Personalization for Federated Diffusion Generative Models
SPIRE adds per-client embeddings to a shared diffusion backbone, enabling parameter-efficient personalization in federated learning, with new-client KID improvements on MNIST, CIFAR-10, and CelebA.