A server-side foundation model can be fine-tuned in a federated way through bidirectional knowledge distillation from lightweight client proxies onto LoRA adapters, improving average top-1 accuracy over FedPromo by 3.9% across five fine-grained domains.
Prometheus [software]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models
A server-side foundation model can be fine-tuned in a federated way through bidirectional knowledge distillation from lightweight client proxies onto LoRA adapters, improving average top-1 accuracy over FedPromo by 3.9% across five fine-grained domains.