English(EN) Guiding Federated Graph Recommendation with LLM-encoded knowledge

LLM指导联邦图推荐系统以提高准确性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-13 12:30

研究人员开发了一个新的框架，该框架利用大型语言模型（LLM）来增强联邦图推荐系统。该方法通过使用LLM编码的知识来指导过程，解决了在联邦学习中聚合分布式、非IID客户端的结构嵌入的挑战。客户端通过冻结的LLM学习本地图表示并将交互模式总结为语义向量，然后中央服务器利用这些向量发现相关的偏好模式并选择性地聚合结构表示。实验表明，该方法比现有的联邦图基线提高了推荐准确性。 AI

影响通过将LLM的语义理解与联邦学习相结合，增强了隐私保护的推荐系统。

排序理由该集群包含一篇详细介绍新颖AI研究框架的学术论文。

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren · 2026-06-16 04:00

Guiding Federated Graph Recommendation with LLM-encoded knowledge

arXiv:2606.15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy. However, aggregati…
arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Zhao Ren · 2026-06-13 12:30

Guiding Federated Graph Recommendation with LLM-encoded knowledge

Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy. However, aggregating graph representations across distributed, non-I…

报道来源 [2]

Guiding Federated Graph Recommendation with LLM-encoded knowledge

Guiding Federated Graph Recommendation with LLM-encoded knowledge

相关实体

相关话题