用轻量大模型和联邦学习实现去中心化个性化推荐
Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations
- 结合轻量LLM与动态个人知识图谱，通过联邦学习进行本地化推理
- 在电影和美食推荐上F1分数提升超4倍，优于现有主流方法
- 适合注重隐私、需个性化推荐的智能应用开发者
个性化推荐日益依赖用户私有数据，推动无需集中数据即可适应个体的方法发展。我们提出联邦目标推荐框架FedTREK-LM，融合轻量级大语言模型（LLM）、动态个人知识图谱（PKG）、联邦学习（FL）及卡尼曼-特沃斯基优化，实现可扩展的去中心化个性化推荐。通过结构化知识图谱提示LLM，FedTREK-LM在电影与食谱推荐等任务中实现上下文感知推理。在三种轻量级Qwen3模型（0.6B、1.7B、4B）上，该框架持续且显著优于当前最先进的知识图谱补全与联邦推荐基线（HAKE、KBGAT、FedKGRec），在电影与食品基准测试中F1分数提升超过4倍。结果还表明真实用户数据对有效个性化至关重要，合成数据会使性能下降最高达46%。总体而言，FedTREK-LM为基于LLM的自适应个性化提供了一种实用范式，可泛化至分散且动态演化的用户知识图谱。
原文摘要 · Abstract (English)
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. By prompting LLMs with structured PKGs, FedTREK-LM performs context-aware reasoning for personalized recommendation tasks such as movie and recipe suggestions. Across three lightweight Qwen3 models (0.6B, 1.7B, 4B), FedTREK-LM consistently and substantially outperforms state-of-the-art KG completion and federated recommendation baselines (HAKE, KBGAT, and FedKGRec), achieving more than a 4x improvement in F1-score on the movie and food benchmarks. Our results further show that real user data is critical for effective personalization, as synthetic data degrades performance by up to 46%. Overall, FedTREK-LM offers a practical paradigm for adaptive, LLM-powered personalization that generalizes across decentralized, evolving user PKGs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。