AI RESEARCH
Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations
arXiv CS.LG
•
ArXi:2603.13264v1 Announce Type: new Personalized recommendation increasingly relies on private user data, motivating approaches that can adapt to individuals without centralizing their information. We present Federated Targeted Recommendations with Evolving Knowledge graphs and Language Models (FedTREK-LM), a framework that unifies lightweight large language models (LLMs), evolving personal knowledge graphs (PKGs), federated learning (FL), and Kahneman-Tversky Optimization to enable scalable, decentralized personalization.