论文标题
微型：多息候选人检索在线
MiCRO: Multi-interest Candidate Retrieval Online
论文作者
论文摘要
在项目表现出短暂性和时间相关性（例如在社交媒体中）的环境中提供个性化建议提出了一些独特的挑战：（1）在经常创建新项目的环境中，归纳理解短暂的呼吁对物品的吸引力，（2）在参与模式中适应趋势，在这些项目中，项目可能会在相关的情况下进行临时变化（3）均可超过此项目的偏好率，而（3）偏好的偏好范围（3）偏好范围偏好。在这项工作中，我们介绍了Micro，这是一种生成统计框架，该框架对多用途用户的偏好和时间多功能项目表示形式进行了建模。我们的框架是专门制定的，以适应新项目和参与的时间模式。 Micro在两个大规模的用户项目数据集上进行的候选检索实验表明了强烈的经验表现：（1）（用户，用户）遵循交互的开源时间数据集，以及（2）（用户，推文）最喜欢的交互的时间数据集，我们将对社区进行额外贡献。
Providing personalized recommendations in an environment where items exhibit ephemerality and temporal relevancy (e.g. in social media) presents a few unique challenges: (1) inductively understanding ephemeral appeal for items in a setting where new items are created frequently, (2) adapting to trends within engagement patterns where items may undergo temporal shifts in relevance, (3) accurately modeling user preferences over this item space where users may express multiple interests. In this work we introduce MiCRO, a generative statistical framework that models multi-interest user preferences and temporal multi-interest item representations. Our framework is specifically formulated to adapt to both new items and temporal patterns of engagement. MiCRO demonstrates strong empirical performance on candidate retrieval experiments performed on two large scale user-item datasets: (1) an open-source temporal dataset of (User, User) follow interactions and (2) a temporal dataset of (User, Tweet) favorite interactions which we will open-source as an additional contribution to the community.
