Decoupled Entity Representation Learning for Pinterest Ads Ranking
This work addresses the challenge of scalable and effective personalized ads ranking for Pinterest, though it appears incremental as it builds on existing embedding and ranking paradigms.
The paper tackles the problem of constructing user and item embeddings for personalized ads ranking at Pinterest by introducing a decoupled upstream-downstream framework that learns embeddings from diverse data sources and integrates them into downstream tasks like CTR and CVR prediction, resulting in significant performance improvements in both offline and online settings.
In this paper, we introduce a novel framework following an upstream-downstream paradigm to construct user and item (Pin) embeddings from diverse data sources, which are essential for Pinterest to deliver personalized Pins and ads effectively. Our upstream models are trained on extensive data sources featuring varied signals, utilizing complex architectures to capture intricate relationships between users and Pins on Pinterest. To ensure scalability of the upstream models, entity embeddings are learned, and regularly refreshed, rather than real-time computation, allowing for asynchronous interaction between the upstream and downstream models. These embeddings are then integrated as input features in numerous downstream tasks, including ad retrieval and ranking models for CTR and CVR predictions. We demonstrate that our framework achieves notable performance improvements in both offline and online settings across various downstream tasks. This framework has been deployed in Pinterest's production ad ranking systems, resulting in significant gains in online metrics.