摘要
特征工程是影响机器学习算法性能的关键因素之一,随着互联网数据规模的扩大,传统特征工程的人力成本不断增加。为减少对特征工程的依赖,构建一种结合显式和隐式特征交互的融合模型。将稀疏结构单元与残差单元相结合以提取隐式特征,利用压缩交互网络学习显式特征,在最后一层全连接层上将两种特征进行融合。在4种不同数据集上的实验结果表明,该模型相比PNN、DCN等模型具有更好的特征提取结果。
Feature engineering has significant effects on performance of machine learning algorithms,but its cost continues to grow with scaling Internet data.In order to reduce the dependence on feature engineering,this paper proposes a fusion model combining explicit and implicit feature interactions.The sparse structural element and residual element are combined to extract implicit features,and the explicit features are learned by using compressed interactive network.And then,fuses explicit feature vectors with implicit feature vectors on the last fully connected layer.Experimental results on 4 kinds of different datasets show that the proposed model has better feature extraction performance than PNN,DCN and other models.
作者
倪志文
马小虎
孙霄
边丽娜
NI Zhiwen;MA Xiaohu;SUN Xiao;BIAN Lina(School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215000,China)
出处
《计算机工程》
CAS
CSCD
北大核心
2020年第3期87-92,98,共7页
Computer Engineering
基金
江苏省研究生科研与实践创新计划项目(KYCX18_2511)。
关键词
特征工程
深度融合
特征交互
残差单元
压缩交互网络
feature engineering
deep fusion
feature interactions
residual unit
compressed interactive network