Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learning-based approaches have been proposed to overcome this issue, existing approaches typically project each user to a single point in the metric space, and thus do not suffice for properly modeling the intensity and the heterogeneity of user-item relationships in implicit feedback. In this paper, we propose TransCF to discover such latent user-item relationships embodied in implicit user-item interactions. Inspired by the translation mechanism popularized by knowledge graph embedding, we construct user-item specific translation vectors by employing the neighborhood information of users and items, and translate each user toward items according to the user's relationships with the items. Our proposed method outperforms several state-of-the-art methods for top-N recommendation on seven real-world data by up to 17% in terms of hit ratio. We also conduct extensive qualitative evaluations on the translation vectors learned by our proposed method to ascertain the benefit of adopting the translation mechanism for implicit feedback-based recommendations.
The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm
Institute of Information Engineering, CAS（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Alibaba Group（阿里巴巴集团）；Sun Yat-sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）
协作度量学习（CML）最近成为推荐系统（RS）中的一种流行方法，缩小了度量学习和协作过滤之间的差距。遵循RS的惯例，现有的方法在其模型设计中利用唯一的用户表示。本文重点介绍了一个具有挑战性的情况下，用户有多个类别的利益。在这种情况下，我们认为，独特的用户表示可能会导致偏好偏差，特别是当项目类别分布不平衡。为了解决这个问题，我们提出了一种新的方法称为\textit{Diversity-Promoting Collaborative Metric Learning}（DPCML），希望考虑到通常被忽视的少数用户的利益。DPCML背后的关键思想是为系统中的每个用户包括多个表示集。基于此嵌入范式，用户对一个项目的偏好聚合从不同的嵌入之间的最小项目用户的距离用户嵌入集。此外，我们观察到，同一用户的嵌入的多样性在模型中也起着至关重要的作用。为此，我们提出了一个\textit{diversity control regularization}术语，以更好地适应多向量表示策略。从理论上讲，我们表明，DPCML可以很好地推广到看不见的测试数据，通过解决来自最小值的恼人的操作的挑战。在一系列基准数据集上的实验证明了DPCML的有效性。
Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Peng Cheng Laboratory（鹏城实验室）
Improved Diversity-Promoting Collaborative Metric Learning for Recommendation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Alibaba Group（阿里巴巴集团）；Sun Yat-sen University（中山大学）；Peng Cheng Laboratory（鹏城实验室）
Preference or Intent? Double Disentangled Collaborative Filtering
HKUST Fok Ying Tung Research Institute（香港科技大学霍英东研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；BOSS Zhipin（BOSS直聘）；University of Science and Technology of China（中国科学技术大学）
Discrete Scale-invariant Metric Learning for Efficient Collaborative Filtering
Faculty of Science and Technology, Charles Darwin University（查尔斯达尔文大学科学技术学院）；University of Electronic Science and Technology of China（电子科技大学）；Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（电子科技大学深圳高等研究院）
