arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.09693cs.IRcs.LG
收藏

EfficientRec:一种基于聚类和用户交互嵌入画像的无限用户-物品规模推荐系统

EfficientRec an unlimited user-item scale recommendation system based on clustering and users interaction embedding profile

Viettel Telecom - Viettel Group(越南电信集团 - 越南电信公司);University of Engineering and Technology - Vietnam National University(越南国立大学 - 工程技术大学)

Vu Hong Quan, Le Hoang Ngan, Le Minh Duc, Nguyen Tran Ngoc Linh, Hoang Quynh-Le

AI总结:

针对传统推荐算法复杂度随用户与物品规模增长的问题,提出 EfficientRec,结合图神经网络、对比学习和软聚类,在保持高准确率的同时降低训练与推理成本并支持无限规模扩展。

摘要:

推荐系统是当前科技公司高度关注的技术。随着业务不断增长,用户和产品数量随时间持续增加,达到非常庞大的规模。传统推荐算法的复杂度依赖于用户和物品数量,因此难以适应工业环境。本文提出一种新方法,将图神经网络与对比学习框架结合,用于提取用户偏好。我们引入软聚类架构,显著降低推理过程的计算成本。实验表明,该模型能够在训练和预测两个阶段以较低计算成本学习用户偏好,同时取得非常好的准确率。我们将该架构命名为 EfficientRec,寓意模型紧凑,并具备扩展至无限用户和产品规模的能力。

英文摘要:

Recommendation systems are highly interested in technology companies nowadays. The businesses are constantly growing users and products, causing the number of users and items to continuously increase over time, to very large numbers. Traditional recommendation algorithms with complexity dependent on the number of users and items make them difficult to adapt to the industrial environment. In this paper, we introduce a new method applying graph neural networks with a contrastive learning framework in extracting user preferences. We incorporate a soft clustering architecture that significantly reduces the computational cost of the inference process. Experiments show that the model is able to learn user preferences with low computational cost in both training and prediction phases. At the same time, the model gives a very good accuracy. We call this architecture EfficientRec with the implication of model compactness and the ability to scale to unlimited users and products.

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。

↑