Deep Neural Networks for YouTube Recommendations

@inproceedings{Covington2016DeepNN,
  title={Deep Neural Networks for YouTube Recommendations},
  author={Paul Covington and Jay L. Adams and Emre Sargin},
  booktitle={RecSys '16},
  year={2016}
}
  • Paul Covington, Jay L. Adams, Emre Sargin
  • Published in RecSys '16 2016
  • Computer Science
  • YouTube represents one of the largest scale and most sophisticated industrial recommendation systems in existence. In this paper, we describe the system at a high level and focus on the dramatic performance improvements brought by deep learning. The paper is split according to the classic two-stage information retrieval dichotomy: first, we detail a deep candidate generation model and then describe a separate deep ranking model. We also provide practical lessons and insights derived from… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 548 CITATIONS

    An empirical investigation of the challenges of real-world reinforcement learning

    VIEW 6 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Multi-Interest Network with Dynamic Routing for Recommendation at Tmall

    VIEW 17 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Recommending what video to watch next: a multitask ranking system

    VIEW 21 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Fine-Grained Deep Knowledge-Aware Network for News Recommendation with Self-Attention

    • Jie Gao, Xin Xin, +5 authors Ping Guo
    • Computer Science
    • 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI)
    • 2018
    VIEW 4 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Learning Tree-based Deep Model for Recommender Systems

    VIEW 13 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Deep Learning Based Recommender System: A Survey and New Perspectives

    VIEW 7 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Deep learning for tabular data : an exploratory study

    VIEW 10 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Estimating Attention Flow in Online Video Networks

    VIEW 6 EXCERPTS
    CITES METHODS, RESULTS & BACKGROUND
    HIGHLY INFLUENCED

    Exploiting Parallelism Opportunities with Deep Learning Frameworks

    VIEW 4 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2016
    2020

    CITATION STATISTICS

    • 69 Highly Influenced Citations

    • Averaged 167 Citations per year from 2017 through 2019

    • 56% Increase in citations per year in 2019 over 2018