Andrew Zhai

Most state-of-the-art search and recommender systems use neural networks to learn representations of entities like users, queries and content items. Graph neural networks (GNNs) are a useful tool for learning such a representation not only based on the entity itself, but also its relationships with other entities. In this talk, we describe the architecture of deep-learning-based search and recommender systems, show how to apply GNNs learned from billions of nodes and edges to these systems to improve their performance, and discuss the lessons that we learned from our journey at Pinterest.