PM-MoE adds a mixture-of-experts layer over all clients' converged personalized modules, with an energy-based denoiser, and reports modest accuracy improvements across six datasets.
Morris Chang
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
-
PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning
PM-MoE adds a mixture-of-experts layer over all clients' converged personalized modules, with an energy-based denoiser, and reports modest accuracy improvements across six datasets.