We present a novel framework for user representation in large-scale
recommender systems, aiming at effectively representing diverse user taste in a
generalized manner. Our approach employs a two-stage methodology combining
representation learning and transfer learning. The representation learning
model uses an autoencoder that compresses various user features into a
representation space. In the second stage, downstream task-specific models
leverage user representations via transfer learning instead of curating user
features individually. We further augment this methodology on the
representation's input features to increase flexibility and enable reaction to
user events, including new user experiences, in Near-Real Time. Additionally,
we propose a novel solution to manage deployment of this framework in
production models, allowing downstream models to work independently. We
validate the performance of our framework through rigorous offline and online
experiments within a large-scale system, showcasing its remarkable efficacy
across multiple evaluation tasks. Finally, we show how the proposed framework
can significantly reduce infrastructure costs compared to alternative
approaches.

我们提出了一个新颖的框架，用于大规模推荐系统中用户的表示，旨在以一种广义的方式有效地表示多样化的用户喜好。我们的方法采用了一种两阶段的方法，结合表示学习和迁移学习。表示学习模型使用自编码器将各种用户特征压缩成表示空间。在第二阶段，特定于任务的下游模型通过迁移学习利用用户表示，而不是单独地整理用户特征。我们进一步改进了这种方法的输入特征，以增加灵活性并实现对用户事件（包括新用户体验）的近实时反应。此外，我们提出了一种新的解决方案，以管理此框架在生产模型中的部署，允许下游模型独立工作。我们通过大规模系统中的严格离线和在线实验验证了我们框架的性能，展示了其在多个评估任务中的显着功效。最后，我们展示了所提出的框架如何显著降低基础设施成本，相比于其他方法。