By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.
Bgefl: Enabling communication-efficient federated learning via bandit gradient estimation in resource-constrained networks.IEEE Transactions on Networking, 2025b
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
A priority-aware learning-unlearning framework with orthogonal LoRA enables robust correction for device join/leave events in dynamic decentralized federated LLM fine-tuning.
citing papers explorer
-
Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
By sharing the B matrix across adapters instead of the A matrix, ALoRA and Fed-ALoRA deliver more balanced performance in multi-task and federated LLM fine-tuning.
-
Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning
A priority-aware learning-unlearning framework with orthogonal LoRA enables robust correction for device join/leave events in dynamic decentralized federated LLM fine-tuning.