arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.01012cs.IRcs.LG
收藏

面向推荐的改进型多样性促进协同度量学习

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)

Shilong Bao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang

AI总结:

本文提出多样性促进协同度量学习DPCML,通过为每个用户引入多向量表示并设计多样性控制正则化方案,缓解多兴趣场景下的偏好偏差,同时从OPAUC角度改进负采样策略,在多个基准数据集上验证了其有效性。

摘要:

协同度量学习(Collaborative Metric Learning, CML)近年来已成为推荐系统(RS)中的一种流行方法,弥合了度量学习与协同过滤之间的差距。遵循推荐系统的惯例,现有方法在其模型设计中利用唯一的用户表示。本文关注一个具有挑战性的场景:用户具有多个兴趣类别。在该设定下,唯一的用户表示可能会引入偏好偏差,尤其是当物品类别分布不平衡时。为解决这一问题,我们提出了一种名为多样性促进协同度量学习(Diversity-Promoting Collaborative Metric Learning, DPCML)的新方法,旨在考虑通常被忽略的用户少数兴趣。DPCML 背后的核心思想是为系统中的每个用户引入一组多个表示,其中用户对物品的偏好通过取其嵌入集合中物品-用户距离的最小值来聚合。具体而言,我们实例化了两种有效的分配策略,以探索每个用户合适的向量数量。同时,我们开发了一种多样性控制正则化方案(Diversity Control Regularization Scheme, DCRS),以更好地适应多向量表示策略。理论上,我们证明 DPCML 相比传统 CML 可以产生更小的泛化误差。此外,我们注意到基于 CML 的方法通常需要负采样来减少其中成对目标所带来的沉重计算负担。在本文中,我们从单向部分 AUC(One-Way Partial AUC, OPAUC)的角度揭示了广泛采用的硬感知采样的根本局限性,然后为基于 CML 的范式开发了一种有效的采样替代方案。最后,在一系列基准数据集上的综合实验证明了 DPCML 的有效性。代码可在 \url{https://github.com/statusrank/LibCML} 获取。

英文摘要:

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called \textit{Diversity-Promoting Collaborative Metric Learning} (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to introduce a set of multiple representations for each user in the system where users' preference toward an item is aggregated by taking the minimum item-user distance among their embedding set. Specifically, we instantiate two effective assignment strategies to explore a proper quantity of vectors for each user. Meanwhile, a \textit{Diversity Control Regularization Scheme} (DCRS) is developed to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could induce a smaller generalization error than traditional CML. Furthermore, we notice that CML-based approaches usually require \textit{negative sampling} to reduce the heavy computational burden caused by the pairwise objective therein. In this paper, we reveal the fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective and then develop an effective sampling alternative for the CML-based paradigm. Finally, comprehensive experiments over a range of benchmark datasets speak to the efficacy of DPCML. Code are available at \url{https://github.com/statusrank/LibCML}.

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。

↑