摘要
点击率(Click-Through Rate,CTR)预测是推荐系统中一项重要的任务,其目标是预测用户点击一个广告或者商品的概率。特征嵌入和特征组合是影响预测性能的关键,因此很多点击率预测模型的思路也是针对这两个方面进行优化。但目前大部分工作仅关注其中一个方面,并且几乎所有的模型在进行特征组合时都没有对特征进行区分,同一个特征与其他特征组合时都使用相同的嵌入和组合方法,阻碍了模型性能的提升。为解决该问题,提出了Auto-SEI(Automatic Super-field-aware Feature Embedding and Interacting)模型。该模型先将每个特征子域分配给一个特征超域,再根据分组得到特征的嵌入,然后为特征对选择合适的组合方法获取组合特征,最后进行预测。Auto-SEI模型中,特征子域的划分和组合方法的选择被参数化为架构搜索问题,利用神经架构搜索(Neural Architecture Search,NAS)算法压缩搜索空间并进行选择。在3个真实的大规模数据集上进行了大量实验,结果表明Auto-SEI模型在点击率预测任务上具有优秀的性能。
Click-through rate(CTR)prediction is an important task in the recommendation system.Its goal is to predict the pro-bability of a user clicking on an advertisement or item.Feature embedding and feature interacting are critical for prediction performance.Therefore,the ideas of many click-through rate prediction models are optimized based on these two aspects.However,most of the work only focus on one of the aspects,and almost all models do not distinguish features in feature interacting.The same embedding and interacting method are used when crossing the same feature with other features,which hinders the improvement of model performance.In order to solve this problem,the automatic super-field-aware feature embedding and interacting(Auto-SEI)model is proposed.Firstly,it assigns each sub-field to a super-field,and obtains the feature embedding according to the grouping,then selects appropriate interacting method for the feature pair to obtain the cross feature,and finally makes prediction.In Auto-SEI model,the division of sub-field and the selection of interacting methods are parameterized as an architecture search problem,and the neural architecture search(NAS)algorithm is used to compress the search space and make selections.A large number of experiments are conducted on three real large-scale data sets and the results show the excellent performance of the Auto-SEI model on the task of click-through rate prediction.
作者
帅剑波
王金策
黄飞虎
彭舰
SHUAI Jian-bo;WANG Jin-ce;HUANG Fei-hu;PENG Jian(College of Computer Science,Sichuan University,Chengdu 610065,China)
出处
《计算机科学》
CSCD
北大核心
2022年第7期10-17,共8页
Computer Science
基金
国家重点研发计划(2017YFB0202403)
四川省重点研发计划(2020YFG0308,2019YFG0494,2020YFG0304,2017GZDZX0003)。
关键词
神经架构搜索
点击率预测
特征嵌入
特征组合
推荐系统
Neural Architecture Search
Click-Through rate prediction
Feature embedding
Feature interacting
Recommendation system
