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
Proceedings ArticleDOI
Characterizing Deep Learning Training Workloads on Alibaba-PAI
TL;DR: An analytical framework is established to investigate detailed execution time breakdown of various workloads using different training architectures, to identify performance bottleneck, and shows that weight/gradient communication during training takes almost 62% of the total execution time among all the workloads on average.
Journal ArticleDOI
Discoverability: Toward a Definition of Content Discovery Through Platforms:
Fenwick McKelvey,Robert Hunt +1 more
TL;DR: An analytical framework for studying the dynamic and personalized processes of content discovery on platforms is proposed that highlights three dimensions of this process: the design and management of choice in platform interfaces, the pathways users take to find content and the effects those choices have, and the resulting experiences these elements produce.
Proceedings ArticleDOI
M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
TL;DR: In this paper, a multi-task multi-view graph representation learning framework (M2GRL) is proposed to learn node representations from multiview graphs for web-scale recommender systems.
Proceedings ArticleDOI
Fast Item Ranking under Neural Network based Measures
TL;DR: This paper formulate ranking under neural network based measures as a generic ranking task, Optimal Binary Function Search (OBFS), which does not make strong assumptions for the ranking measures, and proposes a flexible graph-based solution for it, Binary Function search on Graph (BFSG).
Journal ArticleDOI
Is deep learning better than traditional approaches in tag recommendation for software information sites
TL;DR: This paper testifies that using appropriate deep learning approaches can indeed achieve better performance than traditional approaches in tag recommendation tasks for software information sites.
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.