融合特征选择和交叉网络的增强推荐模型  

Enhanced Recommendation Model Integrating Feature Selection and Cross Network

作　　者：师欣雨 林珊玲 刘珂 林坚普 吕珊红 林志贤[1,2,3] 郭太良 SHI Xin-Yu;LIN Shan-Ling;LIU Ke;LIN Jian-Pu;LYU Shan-Hong;LIN Zhi-Xian;GUO Tai-Liang(School of Advanced Manufacturing,Fuzhou University,Quanzhou 362251,China;Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China,Fuzhou 350108,China;College of Physics and Information Engineering,Fuzhou University,Fuzhou 350116,China)

机构地区：[1]福州大学先进制造学院,泉州362251 [2]闽都创新实验室(中国福建光电信息科学与技术创新实验室),福州350108 [3]福州大学物理与信息工程学院,福州350116

出　　处：《计算机系统应用》2024年第12期97-105,共9页Computer Systems & Applications

基　　金：国家重点研发计划(2021YFB3600603)。

摘　　要：针对目前大多数推荐模型在特征交互时,存在忽视特征重要程度使得推荐模型准确率不高的问题,为此本文提出融合特征选择和交叉网络的增强推荐模型.该模型采用SENet网络在特征交互前过滤不重要的特征,使其挖掘到更有价值的交互信息.在此基础上,进一步使用并行的交叉网络和深度神经网络,以捕捉显式特征交互和隐式特征交互.同时,在交叉网络中引入低秩技术,将权重向量改进为低秩矩阵,在保证模型性能的同时,降低模型的训练成本.该模型在MovieLens-1M、Criteo数据集上与其他推荐模型进行了对比实验,实验结果表明所提推荐模型在AUC指标上明显优于其他模型,证明了所提推荐模型的有效性.Most current recommendation models often overlook the importance of features during feature interactions,leading to low accuracy.To address this issue,an enhanced recommendation model combining feature selection and the cross network is proposed.The SENet network is employed to filter out unimportant features before feature interaction,enabling the extraction of more valuable interaction information.On this basis,parallel cross network and deep neural network are utilized to capture explicit and implicit feature interactions.Additionally,low-rank techniques are introduced in the cross network,transforming weight vectors into low-rank matrices to maintain model performance and reduce model training costs.Comparative experiments on the datasets of MovieLens-1M and Criteo demonstrate that the proposed recommendation model is significantly superior to other models in terms of AUC metrics,which proves the effectiveness of the proposed recommendation model.

关 键 词：推荐算法 深度学习 SENet网络 特征交互 低秩矩阵 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]