AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

A Unified Federated Framework for Trajectory Data Preparation via LLMs

Zhihao Zeng, Ziquan Fang, Wei Shao, Lu Chen, Yunjun Gao

ICLR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TKE (trajectory knowledge enhancer) (ablation)FedTDP · 10 TDP tasksoverall performance: at least 27.52% degradation without TKEImproved
add TPA (privacy autoencoder) (ablation)FedTDP · 10 TDP tasksoverall performance: approximately 5GB additional communication over 10 roundsHurt
add FPO (federated parallel optimization) (ablation)FedTDP · 10 TDP tasksruntime and communication: almost 4 times lessImproved
use FedTDP instead of single-task methodsS-TDP · Table 2 tasksF1/accuracy: at least 18.38% improvementImproved
use FedTDP instead of tabular LLM methodsFM4DP, MELD, TableGPT · Table 2 tasksF1/accuracy: at least 32.26%Improved
use FedTDP instead of spatio-temporal LLM methodsPromptGAT, UniST, UrbanGPT · Table 2 tasksF1/accuracy: 4.84% to 45.22%Improved
train on more tasks (multi-task) (ablation)FedTDP · 10 TDP tasksperformance: falls below S-TDP in Table 2 when trained on one taskImproved
use FedTDP framework for trainingLLM-based baselines · training efficiencyruntime: reduced by a factor of 11.3 to 14.2Improved
use FedTDP at test timeLLM-based baselines · testing efficiencyruntime: 2.6 to 4.8 times lowerImproved
transmit only data needed for cross-client TDPFedTDP · testing efficiencycommunication size: 1.4 to 1.8 times lessImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy