A federated framework using LLMs and SLMs with an autoencoder, prompt-based knowledge enhancement, and split learning claims to handle ten trajectory data preparation tasks while protecting privacy.
Given the number of trajectories|D| in the client, the complexity of Algorithm 2 isO(|D|∗ TR∗ MC ′ ), where MC ′ is the model complexity of the SLM
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
-
FedTDP: A Privacy-Preserving and Unified Framework for Trajectory Data Preparation via Federated Learning
A federated framework using LLMs and SLMs with an autoencoder, prompt-based knowledge enhancement, and split learning claims to handle ten trajectory data preparation tasks while protecting privacy.