arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07976cs.IRcs.AIcs.LG
收藏

跨领域和跨系统建议的统一框架

A Unified Framework for Cross-Domain and Cross-System Recommendations

Ant Group(蚂蚁集团);Macquarie University(麦考瑞大学)

Feng Zhu, Yan Wang, Jun Zhou, Chaochao Chen, Longfei Li, Guanfeng Liu

摘要:

跨域推荐(CDR)和跨系统推荐(CSR)被提出来在具有相对丰富信息的源数据集的帮助下提高目标数据集(域/系统)的推荐准确性。然而,大多数现有的CDR和CSR方法是单目标的,即存在单个目标数据集,这只能帮助目标数据集,因此不能使源数据集受益。在本文中,我们关注三个新的场景,即,双目标CDR(DTCDR),多目标CDR(MTCDR)和CDR+CSR,旨在同时提高所有场景下所有数据集的推荐准确性。为此,我们提出了一个统一的框架,称为GA(基于图形嵌入和注意力技术),用于所有三种情况。在遗传算法中,我们首先构建独立的异构图,以生成更具代表性的用户和项目嵌入。然后,我们提出了一个元素明智的注意力机制,有效地结合嵌入的共同实体(用户/项目)从不同的数据集学习。此外,为了避免负迁移,我们进一步提出了一种个性化的训练策略,以最大限度地减少丰富数据集和稀疏数据集之间的公共实体嵌入差异,导出了三个新模型,即,GA-DTCDR-P、GA-MTCDR-P和GA-CDR+CSR-P。在四个真实世界的数据集上进行的大量实验表明,我们提出的GA模型显着优于最先进的方法。

英文摘要:

Cross-Domain Recommendation (CDR) and Cross-System Recommendation (CSR) have been proposed to improve the recommendation accuracy in a target dataset (domain/system) with the help of a source one with relatively richer information. However, most existing CDR and CSR approaches are single-target, namely, there is a single target dataset, which can only help the target dataset and thus cannot benefit the source dataset. In this paper, we focus on three new scenarios, i.e., Dual-Target CDR (DTCDR), Multi-Target CDR (MTCDR), and CDR+CSR, and aim to improve the recommendation accuracy in all datasets simultaneously for all scenarios. To do this, we propose a unified framework, called GA (based on Graph embedding and Attention techniques), for all three scenarios. In GA, we first construct separate heterogeneous graphs to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common entities (users/items) learned from different datasets. Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i.e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively. Extensive experiments conducted on four real-world datasets demonstrate that our proposed GA models significantly outperform the state-of-the-art approaches.

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。

↑