An adaptive gradient-similarity criterion dynamically selects collaboration partners in personalized federated learning, provably recovering the oracle-optimal sample complexity of All-for-one without knowing client heterogeneity or target accuracy in advance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive collaboration for online personalized distributed learning with heterogeneous clients
An adaptive gradient-similarity criterion dynamically selects collaboration partners in personalized federated learning, provably recovering the oracle-optimal sample complexity of All-for-one without knowing client heterogeneity or target accuracy in advance.