Full Stage Learning to Rank: A Unified Framework for Multi-Stage Systems

no code implementations • 8 May 2024 • Kai Zheng, Haijun Zhao, Rui Huang, Beichuan Zhang, Na Mou, Yanan Niu, Yang song, Hongning Wang, Kun Gai

To address this issue, we propose an improved ranking principle for multi-stage systems, namely the Generalized Probability Ranking Principle (GPRP), to emphasize both the selection bias in each stage of the system pipeline as well as the underlying interest of users.

Information Retrieval Learning-To-Rank +3

SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems

no code implementations • 18 Aug 2023 • Beichuan Zhang, Chenggen Sun, Jianchao Tan, Xinjun Cai, Jun Zhao, Mengqi Miao, Kang Yin, Chengru Song, Na Mou, Yang song

Increasing the size of embedding layers has shown to be effective in improving the performance of recommendation models, yet gradually causing their sizes to exceed terabytes in industrial recommender systems, and hence the increase of computing and storage costs.

Model Compression Quantization +1