DeepFM: a factorization-machine based neural network for CTR prediction
Huifeng Guo,Ruiming Tang,Yunming Ye,Zhenguo Li,Xiuqiang He +4 more
- pp 1725-1731
TLDR
This paper shows that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions, and combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture.Abstract:
Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or require expertise feature engineering. In this paper, we show that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions. The proposed model, DeepFM, combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture. Compared to the latest Wide & Deep model from Google, DeepFM has a shared input to its "wide" and "deep" parts, with no need of feature engineering besides raw features. Comprehensive experiments are conducted to demonstrate the effectiveness and efficiency of DeepFM over the existing models for CTR prediction, on both benchmark data and commercial data.read more
Citations
More filters
Proceedings ArticleDOI
Recommender Systems for Online Video Game Platforms: the Case of STEAM
TL;DR: This work test the potential of state-of-the-art recommender models based respectively on Factorization Machines, deep neural networks and one derived from the mixture of both chosen for their potential of receiving multiple inputs as well as different types of input variables.
Proceedings ArticleDOI
Convolutional Neural Networks based Click-Through Rate Prediction with Multiple Feature Sequences.
TL;DR: Whether and how the feature sequence affects the performance of the CNN-based CTR prediction method is investigated and a method of generating a set of embedding sequences which aims to consider the combined influence of all feature pairs on feature learning is introduced.
Journal ArticleDOI
Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-start Users
TL;DR: ConTS as discussed by the authors unifies attributes and items in the same arm space and achieves their exploration-exploitation (EE) trade-offs automatically using the framework of Thompson sampling.
Journal ArticleDOI
Learning and Fusing Multiple User Interest Representations for Micro-Video and Movie Recommendations
TL;DR: This paper considers efficient representations of four aspects of user interest and proposes item-level representation, which is learned from and integrates the features of a user's historical items, and investigates neighbor-assisted representation, i.e. using neighboring users’ information to characterize user interest collaboratively.
Journal ArticleDOI
Analysis on the “Douyin (Tiktok) Mania” Phenomenon Based on Recommendation Algorithms
TL;DR: The author analyzes algorithm principles used in Douyin and finds that there is a closed-loop relationship between DouyIn addiction and algorithm optimization, which positively effects users’ continuance intention.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings ArticleDOI
Deep Neural Networks for YouTube Recommendations
TL;DR: 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.
Proceedings ArticleDOI
Factorization Machines
TL;DR: Factorization Machines (FM) are introduced which are a new model class that combines the advantages of Support Vector Machines (SVM) with factorization models and can mimic these models just by specifying the input data (i.e. the feature vectors).
Proceedings ArticleDOI
Restricted Boltzmann machines for collaborative filtering
TL;DR: This paper shows how a class of two-layer undirected graphical models, called Restricted Boltzmann Machines (RBM's), can be used to model tabular data, such as user's ratings of movies, and demonstrates that RBM's can be successfully applied to the Netflix data set.