PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest
This work addresses the problem of improving personalized recommendations for users at Pinterest, though it is incremental as it builds on existing embedding approaches.
The paper tackles the limitation of single user embeddings in recommender systems by introducing PinnerSage, a multi-modal user embedding framework that clusters user actions and uses medoids for efficiency, resulting in significantly outperforming single embedding methods in offline and online A/B experiments at Pinterest.
Latent user representations are widely adopted in the tech industry for powering personalized recommender systems. Most prior work infers a single high dimensional embedding to represent a user, which is a good starting point but falls short in delivering a full understanding of the user's interests. In this work, we introduce PinnerSage, an end-to-end recommender system that represents each user via multi-modal embeddings and leverages this rich representation of users to provides high quality personalized recommendations. PinnerSage achieves this by clustering users' actions into conceptually coherent clusters with the help of a hierarchical clustering method (Ward) and summarizes the clusters via representative pins (Medoids) for efficiency and interpretability. PinnerSage is deployed in production at Pinterest and we outline the several design decisions that makes it run seamlessly at a very large scale. We conduct several offline and online A/B experiments to show that our method significantly outperforms single embedding methods.