Off-policy Learning in Two-stage Recommender Systems
Jiaqi Ma, Zhe Zhao, Xinyang Yi, Ji Yang, Minmin Chen, Jiaxi Tang, Lichan Hong, Ed H.
Abstract
Many real-world recommender systems need to be highly scalable: matching millions of items with billions of users, with milliseconds latency. The scalability requirement has led to widely used two-stage recommender systems, consisting of efficient candidate generation model(s) in the first stage and a more powerful ranking model in the second stage.
Topics & Concepts
Recommender systemComputer scienceScalabilityLatency (audio)Ranking (information retrieval)Matching (statistics)Stage (stratigraphy)Information retrievalMachine learningArtificial intelligenceDatabaseTelecommunicationsPaleontologyMathematicsStatisticsBiologyRecommender Systems and TechniquesAdvanced Bandit Algorithms ResearchMachine Learning and Algorithms