Deep Candidate Generation plays an important role in large-scale recommender systems. It takes user history behaviors as inputs and learns user and item latent embeddings for candidate generation. In the literature, conventional methods suffer from two problems. First, a user has multiple embeddings to reflect various interests, and such number is fixed. However, taking into account different levels of user activeness, a fixed number of interest embeddings is sub-optimal. For example, for less active users, they may need fewer embeddings to represent their interests compared to active users. Second, the negative samples are often generated by strategies with unobserved supervision, and similar items could have different labels. Such a problem is termed as class collision. In this paper, we aim to advance the typical two-tower DNN candidate generation model. Specifically, an Adaptive Interest Selection Layer is designed to learn the number of user embeddings adaptively in an end-to-end way, according to the level of their activeness. Furthermore, we propose a Prototypical Contrastive Learning Module to tackle the class collision problem introduced by negative sampling. Extensive experimental evaluations show that the proposed scheme remarkably outperforms competitive baselines on multiple benchmarks.
翻译:深生者在大型推荐人系统中扮演着重要角色。 它将用户历史行为视为投入, 并学习为候选人生成的用户和物品潜伏嵌入。 在文献中, 传统方法存在两个问题。 首先, 用户有多个嵌入, 以反映各种利益, 并且这个数目是固定的。 但是, 考虑到用户活动的不同程度, 固定数量的嵌入兴趣是亚最佳的。 例如, 对于活动较少的用户来说, 他们可能需要较少的嵌入来代表他们的利益。 其次, 负面的样本往往是由未经观察的监督产生的战略生成的, 类似项目可能具有不同的标签。 这样的问题被称为阶级碰撞 。 在本文中, 我们的目标是推进典型的两端 DNNE 候选生成模式。 具体地说, 一个适应性利益选择图旨在了解用户在端到端的适应性嵌入数量, 与其活跃程度相比。 此外, 我们提议一个 Protocrogic 对比性学习模块, 以解决通过负抽样引入的分类碰撞问题。 广泛的实验性评估显示, 具有竞争力的多级基准 。