A threshold-based asynchronous federated learning strategy for fine-tuning LLMs on IoT data reports modest accuracy gains and large latency/throughput wins over FedAvg and FedOpt on the IoT-23 dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
LLMs meet Federated Learning for Scalable and Secure IoT Management
A threshold-based asynchronous federated learning strategy for fine-tuning LLMs on IoT data reports modest accuracy gains and large latency/throughput wins over FedAvg and FedOpt on the IoT-23 dataset.