2026
FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources
ICML 2026poster
Driven by the imperative to leverage privacy-sensitive data scattered across decentralized devices, federated fine-tuning has emerged as a vital paradigm for adapting large language models without compromising data privacy. Yet, its practical efficacy is bottlenecked by severe client resource hetero…