arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.16066cs.AI
收藏

用于动态推荐的时序图网络框架

A Temporal Graph Network Framework for Dynamic Recommendation

Ulsan National Institute of Science and Technology(蔚山国立科学技术院);Carnegie Mellon University(卡内基梅隆大学)

Yejin Kim, Youngbin Lee, Vincent Yuan, Annika Lee, Yongjae Lee

AI总结:

本研究首次将 Temporal Graph Networks (TGN) 直接应用于推荐系统,利用真实数据集及多种图和历史嵌入方法,验证了其在动态推荐场景中的适应性和有效性。

摘要:

推荐系统对电子商务和流媒体服务等平台的用户参与度至关重要,但由于依赖静态数据,往往滞后于用户不断变化的偏好。Temporal Graph Networks (TGNs) 提出后,多项研究表明 TGN 能显著改善节点和边特征随时间动态变化的场景。然而,尽管其潜力巨大,迄今为止尚未直接应用于推荐系统。本研究通过在推荐系统中直接实现 Temporal Graph Networks (TGN) 弥补了这一空白,这在该领域尚属首次。利用真实世界数据集及一系列图和历史嵌入方法,我们展示了 TGN 的适应性,证实了其在动态推荐场景中的有效性。

英文摘要:

Recommender systems, crucial for user engagement on platforms like e-commerce and streaming services, often lag behind users' evolving preferences due to static data reliance. After Temporal Graph Networks (TGNs) were proposed, various studies have shown that TGN can significantly improve situations where the features of nodes and edges dynamically change over time. However, despite its promising capabilities, it has not been directly applied in recommender systems to date. Our study bridges this gap by directly implementing Temporal Graph Networks (TGN) in recommender systems, a first in this field. Using real-world datasets and a range of graph and history embedding methods, we show TGN's adaptability, confirming its effectiveness in dynamic recommendation scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑