FedQuad adaptively picks how many final layers each device trains and how many layers' activations are compressed, reporting 1.4-5.3x faster convergence than federated fine-tuning baselines.
The eu general data protec- tion regulation (gdpr),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuning
FedQuad adaptively picks how many final layers each device trains and how many layers' activations are compressed, reporting 1.4-5.3x faster convergence than federated fine-tuning baselines.