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
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
TL;DR: This work proposes a cross-modal attention model called X-Pool that reasons between a text and the frames of a video, and generates an aggregated video representation conditioned on the text's attention weights over the frames.
Proceedings ArticleDOI
AutoDim: Field-aware Embedding Dimension Searchin Recommender Systems
Xiangyu Zhao,Haochen Liu,Hui Liu,Jiliang Tang,Weiwei Guo,Jun Shi,Sida Wang,Huiji Gao,Bo Long +8 more
TL;DR: In this paper, an AutoML-based framework (AutoDim) is proposed to automatically select dimensions for different feature fields in a data-driven fashion, which can calculate the weights over various dimensions in a soft and continuous manner for feature fields.
Proceedings ArticleDOI
Degenerate Feedback Loops in Recommender Systems
TL;DR: In this article, the role of user dynamics and the behavior of recommender systems is examined and a theoretical analysis is provided to disentangle the echo chamber from the filter bubble effect.
Journal ArticleDOI
Exploring Echo-Systems: How Algorithms Shape Immersive Media Environments.
TL;DR: This paper attempts to analyze the process in which fake news proliferates social networking sites and presents a method of understanding and articulating ways in which personalized feeds are shaped by algorithm-based user feedback.
Proceedings ArticleDOI
KRED: Knowledge-Aware Document Representation for News Recommendations
TL;DR: Zhang et al. as discussed by the authors proposed KRED, which is a fast and effective model to enhance arbitrary document representation with a knowledge graph by attentively aggregating information from their neighborhood in the knowledge graph and then a context embedding layer is applied to annotate the dynamic context of different entities such as frequency, category and position.
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.