Deep Interest Network for Click-Through Rate Prediction
Guorui Zhou,Xiaoqiang Zhu,Chenru Song,Ying Fan,Han Zhu,Xiao Ma,Yan Yanghui,Junqi Jin,Han Li,Kun Gai +9 more
- pp 1059-1068
Reads0
Chats0
TLDR
A novel model: Deep Interest Network (DIN) is proposed which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad.Abstract:
Click-through rate prediction is an essential task in industrial applications, such as online advertising. Recently deep learning based models have been proposed, which follow a similar Embedding&MLP paradigm. In these methods large scale sparse input features are first mapped into low dimensional embedding vectors, and then transformed into fixed-length vectors in a group-wise manner, finally concatenated together to fed into a multilayer perceptron (MLP) to learn the nonlinear relations among features. In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are. The use of fixed-length vector will be a bottleneck, which brings difficulty for Embedding&MLP methods to capture user's diverse interests effectively from rich historical behaviors. In this paper, we propose a novel model: Deep Interest Network (DIN) which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad. This representation vector varies over different ads, improving the expressive ability of model greatly. Besides, we develop two techniques: mini-batch aware regularization and data adaptive activation function which can help training industrial deep networks with hundreds of millions of parameters. Experiments on two public datasets as well as an Alibaba real production dataset with over 2 billion samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with state-of-the-art methods. DIN now has been successfully deployed in the online display advertising system in Alibaba, serving the main traffic.read more
Citations
More filters
Proceedings ArticleDOI
HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations
TL;DR: This work proposes a specifically tailor-made Hybrid Static and Adaptive Graph Embedding (HySAGE) network for context-drifting recommendations, to disentangle the relatively static user-item interaction and rapidly drifting contextual features.
Proceedings ArticleDOI
Underestimation Refinement: A General Enhancement Strategy for Exploration in Recommendation Systems
Yuhai Song,Lu Wang,Haoming Dang,Weiwei Zhou,Jing Guan,Xiwei Zhao,Changping Peng,Yongjun Bao,Jingping Shao +8 more
TL;DR: In this article, a general enhancement strategy, Underestimation Refinement (UR), is proposed to explicitly incorporate the prior knowledge that insufficient impressions likely leads to CTR underestimation, which is applicable to almost all the existing exploration methods.
Journal ArticleDOI
Trust Recommendation Based on Deep Deterministic Strategy Gradient Algorithm
TL;DR: Wang et al. as mentioned in this paper proposed a deep reinforcement learning-based recommendation algorithm based on DDPG to capture the changes in user preferences and update the trust between users, which can alleviate data sparseness and enhance the interpretability of results.
Proceedings ArticleDOI
Combo-Fashion: Fashion Clothes Matching CTR Prediction with Item History
TL;DR: A novel algorithm called Combo-Fashion is designed, which extracts the matching effect by introducing the matching history of the combo item with two cascaded modules: (i) Matching Search Module (MSM) seeks the popular combo items and undesirable ones as a positive set and a negative set, respectively; (ii), Matching Prediction Module (MPM) models the precise relationship between the candidate combo item and the positive/negative set by an attention-based deep model.
Proceedings ArticleDOI
Research on User Enhanced Experience for Public Digital Cultural Services
Dawei Wei,Hua Zhang +1 more
TL;DR: A personalized information recommendation service model oriented to "National Library Open Course", and gives a solution to the personalized service recommendation system based on user behavior characteristics, which can effectively solve the problem of unsatisfactory recommendation performance caused by sparse matrix data.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
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.
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.