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
Fine-Grained Deep Knowledge-Aware Network for News Recommendation with Self-Attention
TL;DR: This work introduces a novel self-attention based mechanism in news recommendation that outperforms better results than previous start-of-art recommendation models.
Posted Content
Sequential Evaluation and Generation Framework for Combinatorial Recommender System
TL;DR: This work model the combinatorial recommendation as the problem of generating a sequence of items from a candidate set, with the target of maximizing the expected overall utility of the sequence and proposes the Evaluation-Generation framework.
Journal ArticleDOI
AICF: Attention-based item collaborative filtering
TL;DR: Compared with the state-of-the-art recommendation models, the AICF model with simple attention mechanism Self-Attention can better estimate the weight of historical items on non-sparse data sets and achieves superior recommendation performance on sparse data.
Journal ArticleDOI
Research on Understanding the Effect of Deep Learning on User Preferences
Garima Gupta,Rahul Katarya +1 more
TL;DR: A vast range of scope for efficient recommender systems in future is exhibited, including those that can model the user interactions more accurately and extract sophisticated features to provide recommendations with better accuracy.
Journal ArticleDOI
Recommendation research trends: review, approaches and open issues
Anu Taneja,Anuja Arora +1 more
TL;DR: Details of various public datasets, their corresponding techniques, comparative analysis of existing recommendation approaches based on faced challenges and performance measures are examined and prioritisation of recommendation keywords is presented in form of weighted keyword network.
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.