FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
FedHPro introduces gradient-matched hyper-prototypes plus mutual-contrastive learning to produce semantically consistent global signals and reach state-of-the-art accuracy on heterogeneous image benchmarks.