Deep Neural Networks for YouTube Recommendations
Paul Covington,Jay Adams,Emre Sargin +2 more
- pp 191-198
Reads0
Chats0
TLDR
This paper details a deep candidate generation model and then describes a separate deep ranking model and provides practical lessons and insights derived from designing, iterating and maintaining a massive recommendation system with enormous user-facing impact.Abstract:
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 designing, iterating and maintaining a massive recommendation system with enormous user-facing impact.read more
Citations
More filters
Journal ArticleDOI
Music Video Recommendation Based on Link Prediction Considering Local and Global Structures of a Network
TL;DR: By using the LP-LGSN to predict the degrees to which users desire music videos, the proposed method can recommend users’ desired music videos and the experimental results for a real-world dataset constructed from YouTube-8M show the effectiveness of the method.
Book ChapterDOI
How Facebook and Google Accidentally Created a Perfect Ecosystem for Targeted Disinformation.
TL;DR: This chapter provides examples and discusses relevant mechanisms and interactions of optimization for metrics like dwell time, watch time or “engagement” that can promote disinformation and propaganda content.
Proceedings ArticleDOI
Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information
TL;DR: In this paper, the authors consider the information availability problem through the lens of user recourse and propose a computationally efficient audit for top-$N$ linear recommender models, and describe the relationship between model complexity and the effort necessary for users to exert control over their recommendations.
Posted Content
CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery
Kiwan Maeng,Shivam Bharuka,Isabel Gao,Mark C. Jeffrey,Vikram Saraph,Bor-Yiing Su,Caroline Trippel,Jiyan Yang,Michael G. Rabbat,Brandon Lucia,Carole-Jean Wu +10 more
TL;DR: CPR relaxes the consistency requirement by enabling non-failed nodes to proceed without loading checkpoints when a node fails during training, improving failure-related overheads and suggesting that CPR can speed up training on a real production-scale cluster, without notably degrading the accuracy.
Proceedings ArticleDOI
An Homophily-based Approach for Fast Post Recommendation in Microblogging Systems
TL;DR: After a thorough study of a large Twitter dataset, this work presents a propagation model which relies on homophily to propose post recommendations, and relies on the construction of a similarity graph based on retweet behaviors on top of the Twitter graph.
References
More filters
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Posted Content
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Batch Normalization as mentioned in this paper normalizes layer inputs for each training mini-batch to reduce the internal covariate shift in deep neural networks, and achieves state-of-the-art performance on ImageNet.
Posted Content
Distributed Representations of Words and Phrases and their Compositionality
TL;DR: In this paper, the Skip-gram model is used to learn high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships and improve both the quality of the vectors and the training speed.