A server-side multi-head hypernetwork generates personalized parameters for clients with heterogeneous model architectures, plus an optional global-model distillation variant, and beats several pFL baselines on four benchmarks.
Harmony: Heterogeneous multi-modal federated learning through disentangled model training
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
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Hypernetworks for Model-Heterogeneous Personalized Federated Learning
A server-side multi-head hypernetwork generates personalized parameters for clients with heterogeneous model architectures, plus an optional global-model distillation variant, and beats several pFL baselines on four benchmarks.