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
A Survey on Knowledge Graph-Based Recommender Systems
Jiangzhou Liu,Li Duan +1 more
TL;DR: In this article, the authors collected papers related to knowledge graph-based recommender systems and summarized their fundamental knowledge and main ideas, including the usage of the knowledge graph in the recommender system and user interest models, and proposed several future directions aiming to make some progress.
Proceedings ArticleDOI
Context-aware Youtube recommender system
TL;DR: A context-aware recommender system is proposed for Youtube that keeps track of multiple interests of a user and recommends videos based on their current context only, which serves a user better in finding relevant videos and has higher relevance to human judgment.
Proceedings ArticleDOI
Towards Representation Alignment and Uniformity in Collaborative Filtering
TL;DR: This paper measures the representation quality in CF from the perspective of alignment and uniformity on the hypersphere, and empirically analyzes the learning dynamics of typical CF methods in terms of quantified alignment and uniforms, which shows that better alignment or uniformity both contribute to higher recommendation performance.
Proceedings ArticleDOI
Dual Neural Personalized Ranking
TL;DR: This paper proposes dual neural personalized ranking (DualNPR), which fully exploits both user- and item-side pairwise rankings in a unified manner and is built upon deep matrix factorization to capture the variability of user/item representations.
Dissertation
Trust assessment in large-scale collaborative systems
TL;DR: A trust model for repeated trust game that computes user trust scores based on their past behavior is designed and a trust model to extend to Wikipedia based on user contributions to the quality of the edited Wikipedia articles is extended.
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.