Ranking & Recommendations

Our research aims to build cutting-edge AI that can understand, inspire, and connect people to what's most meaningful to them. We push the state of the art in applied research to learn from large, diverse datasets, and build powerful and flexible frameworks that allow us to train and deploy models at huge scale. These technologies power Facebook products like News Feed, Instagram, Ads, and Search.

Our research areas include Deep Learning, Massive Sparse Data, Behavior Modeling, Graph Learning, Representation Learning, Reinforcement Learning, Optimization, Distributed/GPU Training, Multi-Modality, Visualization, etc.

Latest Publications

December 03, 2018


Training with Low-precision Embedding Tables

Jian Zhang, Jiyan Yang, Hector Yuen

December 03, 2018