CAN:Effective Cross Features by Global Attention Mechanism and Neural Network for Ad Click Prediction

作     者：Wenjie Cai Yufeng Wang Jianhua Ma Qun Jin Wenjie Cai;Yufeng Wang;Jianhua Ma;Qun Jin

作者机构：Nanjing University of Posts and Telecommunications(NJUPT)Nanjing210003China Digital Media Department in the Faculty of Computer and Information SciencesHosei UniversityTokyo 163-8001Japan Networked Information Systems LaboratoryDepartment of Human Informatics and Cognitive SciencesWaseda UniversityTokyo 163-8001Japan 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2022年第27卷第1期

页      码：186-195页

摘      要：Online advertising click-through rate(CTR) prediction is aimed at predicting the probability of a user clicking an ad,and it has undergone considerable development in recent *** of the hot topics in this area is the construction of feature interactions to facilitate accurate *** machine provides second-order feature interactions by linearly multiplying hidden feature ***,real-world data present a complex and nonlinear ***,second-order feature interactions are unable to represent cross information *** drawback has been addressed using deep neural networks(DNNs),which enable high-order nonlinear feature ***,DNN-based feature interactions cannot easily optimize deep structures because of the absence of cross information in the original *** this study,we propose an effective CTR prediction algorithm called CAN,which explicitly exploits the benefits of attention mechanisms and DNN *** attention mechanism is used to provide rich and expressive low-order feature interactions and facilitate the optimization of DNN-based predictors that implicitly incorporate high-order nonlinear feature *** experiments using two real datasets demonstrate that our proposed CAN model performs better than other cross feature-and DNN-based predictors.

主 题 词：click-through rate prediction global attention mechanism feature interaction neural network 

学科分类：050302[050302] 1305[艺术学-设计学类] 12[管理学] 13[艺术学] 1201[管理学-管理科学与工程类] 05[文学] 081104[081104] 08[工学] 0835[0835] 0503[文学-新闻传播学类] 0811[工学-水利类] 0812[工学-测绘类] 

核心收录：

D　O　I：10.26599/TST.2020.9010053

馆 藏 号：203104592...