Many important multiple-objective decision problems can be cast within the framework of ranking under constraints and solved via a weighted bipartite matching linear program. Some of these optimization problems, such as personalized content recommendations, may need to be solved in real time and thus must comply with strict time requirements to prevent the perception of latency by consumers. Classical linear programming is too computationally inefficient for such settings. We propose a novel approach to scale up ranking under constraints by replacing the weighted bipartite matching optimization with a prediction problem in the algorithm deployment stage. We show empirically that the proposed approximate solution to the ranking problem leads to a major reduction in required computing resources without much sacrifice in constraint compliance and achieved utility, allowing us to solve larger constrained ranking problems real-time, within the required 50 milliseconds, than previously reported.
LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation
University of Macau（澳门大学）；University of Pennsylvania（宾夕法尼亚大学）；Tongji University（同济大学）；Juntendo University（立命馆大学）；University of Southampton（南安普顿大学）；University of Bologna（博洛尼亚大学）；Wuhan University（武汉大学）；University of the Chinese Academy of Sciences（中国科学院大学）；Hanyang University（汉阳大学）；Zhejiang University（浙江大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）
SARM: LLM-Augmented Semantic Anchor for End-to-End Live-Streaming Ranking
Kuaishou Technology（快手科技）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
FedFlex: Federated Learning for Diverse Netflix Recommendations
Vrije Universiteit Amsterdam Netherlands；Georgia Institute of Technology Mexico；Centrum Wiskunde \& Informatica Netherlands；Georgia Institute of Technology
