A quadruplet-based loss for federated learning that aims to reduce representational collapse under data heterogeneity, with mixed empirical support.
Model-contrastive federated learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
A quadruplet-based loss for federated learning that aims to reduce representational collapse under data heterogeneity, with mixed empirical support.