摘要
近年来,使用深度学习技术与用户信任信息进行推荐的系统已成为学术界的研究热点之一,但要为推荐系统建立结合了这两者的模型仍是目前学界面临的重要挑战之一。文中提出了一种通过构建联合优化函数来扩展深度自解码器和Top-k语义社交网络信息的混合模型。基于网络表示学习法进行隐性语义信息采集,并使用多个真实社交网络数据集进行实验,通过多种方法评估所述AE-NRL模型(Autoencoder-Network Representation Learning Model)的性能。实验结果表明,所提模型在更稀疏且体量更大的数据集中比矩阵分解法具有更优的性能;相比显性信任链接,隐性且可靠的社交网络信息可更好地识别用户间的信任关系;在网络表示学习技术中,基于深度学习的模型(SDNE和DNGR)在AE-NRL模型中的效果更好。
In recent years,using deep learning technology and user-trusted information to improve the recommendation system has become one of the hot topics in the academia,but it is still one of the important challenges to build a model for the recommendation system which combines the two.This paper proposes a hybrid model that expands the deep self-decoder and Top-k semantic social network information by constructing a joint optimization function.The model would collect implicit semantic information based on the network representation learning method and perform experiments with multiple real social network datasets to eva-luate the performance of the AE-NRL model(Autoencoder-Network Representation Learning Model)by various methods.The results show that the model proposed in this paper has better performance than the matrix decomposition method in more sparse and larger data sets.Compared with explicit trust links,the implicit and reliable social network information can better identify the trust degree between users.In the network representation learning technology,deep learning models(SDNE and DNGR)are more effective in the AE-NRL model.
作者
顾秋阳
琚春华
吴功兴
GU Qiu-yang;JU Chun-hua;WU Gong-xing(School of Management,Zhejiang University of Technology,Hangzhou 310023,China;China Institute for Small and Medium Enterprises,Zhejiang University of Technology,Hangzhou 310023,China;School of Management Science&Engineering,Zhejiang Gongshang University,Hangzhou 310018,China)
出处
《计算机科学》
CSCD
北大核心
2020年第11期101-112,共12页
Computer Science
基金
国家自然科学基金项目(71571162)
浙江省社科规划重点课题(20NDJC10Z)。
关键词
自编码器
网络表示学习
社交网络
信息推荐
用户信任信息
Autoencoder
Network represents learning
Social networks
Information recommendation
User trust information
