DCFM is a new decentralized framework that enforces structural constraints on generative factors across siloed data sources to produce novel compositions via peer interactions.
Training diffusion models with federated learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 4verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
CollaFuse enables collaborative diffusion model training by splitting computation between resource-limited clients and a central server to reduce local burden and raw data sharing.
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustness than VAE or DDPM alternatives.
UMEDA is a new graph federated learning method that uses low-rank spectral filtering and diffusion over a shared integral operator to fuse multi-modal data privately, outperforming baselines on MM-Fi and RELI11D under high heterogeneity and tight privacy budgets.
citing papers explorer
-
Compositional Generative Modeling from Decentralized Data
DCFM is a new decentralized framework that enforces structural constraints on generative factors across siloed data sources to produce novel compositions via peer interactions.
-
CollaFuse: Collaborative Diffusion Models
CollaFuse enables collaborative diffusion model training by splitting computation between resource-limited clients and a central server to reduce local burden and raw data sharing.
-
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustness than VAE or DDPM alternatives.
-
UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
UMEDA is a new graph federated learning method that uses low-rank spectral filtering and diffusion over a shared integral operator to fuse multi-modal data privately, outperforming baselines on MM-Fi and RELI11D under high heterogeneity and tight privacy budgets.