arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.06327cs.IR
收藏

流推荐的双翼混合专家模型

Double-Wing Mixture of Experts for Streaming Recommendations

Yan Zhao, Shoujin Wang, Yan Wang, Hongwei Liu, Weizhe Zhang

摘要:

流推荐系统(SRS)通常仅在新接收的数据上训练推荐模型以解决用户偏好漂移,即,改变用户对物品的偏好。然而,这种做法忽略了历史数据中嵌入的长期用户偏好。更重要的是,数据流中常见的异构性大大降低了流推荐的准确性。原因是不同类型的用户(或项目)的不同偏好(或特征)无法通过统一模型很好地学习。为了解决这两个问题,我们提出了一个变量和水库增强采样的双翼混合专家模型框架,称为VRS-DWMoE,以提高流媒体推荐的准确性。在VRS-DWMoE中,我们首先设计了变分和随机增强的采样,以明智地用历史数据补充新数据,从而在捕获长期用户偏好的同时解决用户偏好漂移问题。在此基础上,我们提出了一个双翼混合专家模型(DWMoE)模型,首先有效地学习异构用户的偏好和项目的特点,然后提出建议的基础上。具体而言,DWMoE包含两混合专家模型(MoE,一个有效的集成学习模型),分别学习用户偏好和项目特征。此外,每个MoE中的多个专家学习不同类型的用户(或项目)的偏好(或特性),其中每个专家专门研究一个基础类型。大量的实验表明,VRS-DWMoE始终优于最先进的SRS。

英文摘要:

Streaming Recommender Systems (SRSs) commonly train recommendation models on newly received data only to address user preference drift, i.e., the changing user preferences towards items. However, this practice overlooks the long-term user preferences embedded in historical data. More importantly, the common heterogeneity in data stream greatly reduces the accuracy of streaming recommendations. The reason is that different preferences (or characteristics) of different types of users (or items) cannot be well learned by a unified model. To address these two issues, we propose a Variational and Reservoir-enhanced Sampling based Double-Wing Mixture of Experts framework, called VRS-DWMoE, to improve the accuracy of streaming recommendations. In VRS-DWMoE, we first devise variational and reservoir-enhanced sampling to wisely complement new data with historical data, and thus address the user preference drift issue while capturing long-term user preferences. After that, we propose a Double-Wing Mixture of Experts (DWMoE) model to first effectively learn heterogeneous user preferences and item characteristics, and then make recommendations based on them. Specifically, DWMoE contains two Mixture of Experts (MoE, an effective ensemble learning model) to learn user preferences and item characteristics, respectively. Moreover, the multiple experts in each MoE learn the preferences (or characteristics) of different types of users (or items) where each expert specializes in one underlying type. Extensive experiments demonstrate that VRS-DWMoE consistently outperforms the state-of-the-art SRSs.

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。

↑