HARMONY mitigates representation skew in heterogeneous hybrid split federated learning via meta-learning to simulate diverse extractors and server-side contrastive learning to align features, delivering up to 43% accuracy gains.
FIARSE: Model- heterogeneous federated learning via importance-aware submodel extraction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning
HARMONY mitigates representation skew in heterogeneous hybrid split federated learning via meta-learning to simulate diverse extractors and server-side contrastive learning to align features, delivering up to 43% accuracy gains.