kNN-Embed：用于多兴趣候选检索的局部平滑嵌入混合
kNN-Embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval
AI总结：
针对单嵌入ANN候选检索多样性不足的问题，提出kNN-Embed方法，将用户表示为多个兴趣簇的平滑混合并按权重查询，从而在三个数据集上显著提升召回率与多样性，并开源Twitter关注图数据集。
摘要：
候选检索是推荐系统的第一阶段，其中使用轻量级系统为输入用户检索潜在相关条目。这些候选项随后在推荐系统的后续阶段使用更复杂的排序模型进行排序和剪枝。作为推荐漏斗的顶部，检索出高召回率的候选集以馈送到下游排序模型非常重要。一种常见方法是利用来自单个稠密查询嵌入的近似最近邻（ANN）搜索；然而，这种方法可能产生低多样性的结果集，其中包含许多近似重复项。由于用户通常具有多个兴趣，候选检索理想情况下应返回反映用户多个兴趣的多样化候选集。为此，我们引入了kNN-Embed，这是一种改进基于稠密ANN检索的多样性的通用方法。kNN-Embed将每个用户表示为学习到的项目簇上的平滑混合，这些簇代表用户不同的“兴趣”。通过按用户的混合权重比例查询用户的每个混合成分，我们检索出反映用户每个兴趣元素的高多样性候选集。我们在三个数据集上通过实验将kNN-Embed与标准ANN候选检索进行比较，并展示了整体召回率的显著提升和多样性的改善。伴随这项工作，我们开源了一个大型Twitter关注图数据集（https://huggingface.co/datasets/Twitter/TwitterFollowGraph），以促进推荐系统中图挖掘和表示学习的进一步研究。
英文摘要：
Candidate retrieval is the first stage in recommendation systems, where a light-weight system is used to retrieve potentially relevant items for an input user. These candidate items are then ranked and pruned in later stages of recommender systems using a more complex ranking model. As the top of the recommendation funnel, it is important to retrieve a high-recall candidate set to feed into downstream ranking models. A common approach is to leverage approximate nearest neighbor (ANN) search from a single dense query embedding; however, this approach this can yield a low-diversity result set with many near duplicates. As users often have multiple interests, candidate retrieval should ideally return a diverse set of candidates reflective of the user's multiple interests. To this end, we introduce kNN-Embed, a general approach to improving diversity in dense ANN-based retrieval. kNN-Embed represents each user as a smoothed mixture over learned item clusters that represent distinct "interests" of the user. By querying each of a user's mixture component in proportion to their mixture weights, we retrieve a high-diversity set of candidates reflecting elements from each of a user's interests. We experimentally compare kNN-Embed to standard ANN candidate retrieval, and show significant improvements in overall recall and improved diversity across three datasets. Accompanying this work, we open source a large Twitter follow-graph dataset (https://huggingface.co/datasets/Twitter/TwitterFollowGraph), to spur further research in graph-mining and representation learning for recommender systems.
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。
