A federated learning method combines client-specific orthogonal transformations on frozen black-box foundation model embeddings with a shared classifier, outperforming baselines on several domain-shift benchmarks.
Language models are few-shot learners
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
-
Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations
A federated learning method combines client-specific orthogonal transformations on frozen black-box foundation model embeddings with a shared classifier, outperforming baselines on several domain-shift benchmarks.