arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2201.05861cs.IRcs.LG
收藏

异构推荐的深度统一表示

Deep Unified Representation for Heterogeneous Recommendation

Alibaba Group(阿里巴巴集团);Ant Financial Services Group(蚂蚁金融服务集团);University of Science and Technology of China(中国科学技术大学)

Chengqiang Lu, Mingyang Yin, Shuheng Shen, Luo Ji, Qi Liu, Hongxia Yang

摘要:

推荐系统一直是学术界和工业界广泛研究的课题。以往的工作主要集中在同类推荐系统上,对于异构推荐系统的研究进展甚微。然而,异构的建议,例如,推荐不同类型的物品,包括产品、视频、名人购物笔记等,如今占主导地位。现有技术的方法不能利用来自不同类型的项目的属性,因此存在数据稀疏性问题。联合表示具有不同特征空间的项目确实是相当具有挑战性的。为了解决这个问题,我们提出了一个基于核的神经网络,即深度统一表示(或DURation)的异构推荐,联合建模异构项目的统一表示,同时保持其原始的特征空间拓扑结构。理论上,我们证明了所提出的模型的表示能力。此外,我们在真实世界的数据集上进行了广泛的实验。实验结果表明,在统一表示的情况下,我们的模型取得了显着的改善(例如,AUC评分提高4.1% ~ 34.9%,在线CTR提高3.7%)。

英文摘要:

Recommendation system has been a widely studied task both in academia and industry. Previous works mainly focus on homogeneous recommendation and little progress has been made for heterogeneous recommender systems. However, heterogeneous recommendations, e.g., recommending different types of items including products, videos, celebrity shopping notes, among many others, are dominant nowadays. State-of-the-art methods are incapable of leveraging attributes from different types of items and thus suffer from data sparsity problems. And it is indeed quite challenging to represent items with different feature spaces jointly. To tackle this problem, we propose a kernel-based neural network, namely deep unified representation (or DURation) for heterogeneous recommendation, to jointly model unified representations of heterogeneous items while preserving their original feature space topology structures. Theoretically, we prove the representation ability of the proposed model. Besides, we conduct extensive experiments on real-world datasets. Experimental results demonstrate that with the unified representation, our model achieves remarkable improvement (e.g., 4.1% ~ 34.9% lift by AUC score and 3.7% lift by online CTR) over existing state-of-the-art models.

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。

↑