韩晨, 杨兴耀, 于炯, 郭亮, 胡皓禹. 基于知识图谱的双重感知网络推荐算法[J]. 微电子学与计算机, 2022, 39(8): 11-20. DOI: 10.19304/J.ISSN1000-7180.2022.0096
引用本文: 韩晨, 杨兴耀, 于炯, 郭亮, 胡皓禹. 基于知识图谱的双重感知网络推荐算法[J]. 微电子学与计算机, 2022, 39(8): 11-20. DOI: 10.19304/J.ISSN1000-7180.2022.0096
HAN Chen, YANG Xingyao, YU Jiong, GUO Liang, HU Haoyu. Knowledge graph double perception network for recommendation algorithm[J]. Microelectronics & Computer, 2022, 39(8): 11-20. DOI: 10.19304/J.ISSN1000-7180.2022.0096
Citation: HAN Chen, YANG Xingyao, YU Jiong, GUO Liang, HU Haoyu. Knowledge graph double perception network for recommendation algorithm[J]. Microelectronics & Computer, 2022, 39(8): 11-20. DOI: 10.19304/J.ISSN1000-7180.2022.0096

基于知识图谱的双重感知网络推荐算法

Knowledge graph double perception network for recommendation algorithm

  • 摘要: 近年来,通过聚合知识图谱中附加的项目信息进行推荐取得了优异的成果,但用户信息来源相对较少,同时多重聚合会使项目自身特征表达不全,甚至发生噪音.针对以上两点,提出基于知识图谱的双重感知网络推荐算法KGDP.首先,从用户交互记录中随机选取部分项目作为用户相关项目,以及选取项目的邻居实体作为项目的相关实体;然后,将选取的用户相关项目经过深度神经网络融合为用户特征,丰富了用户特征,同时单独聚合项目的相关实体;其次,经过两个深度神经网络使用户分别感知项目特征和邻居特征,即非线性交互;最后,通过一个单层感知机调节交互特征的输出权重进行评分预测.在推荐算法常用的两个真实数据集上进行实验,较基线模型AUC指标分别提升了9.2%、2.4%;ACC指标提升了6.6%、1.9%,F1指标分别提升了7.0%、1.1%;Precision@N指标分别提升了28.8%、6.5%;Recall@N分别提升了4.0%、23.7%;F1@N指标分别提升了43.3%、8.4%.

     

    Abstract: In recent years, excellent results have been achieved by aggregating the additional item information in the knowledge graph, but there are relatively few sources of user information. At the same time, multiple aggregation will make the expression of the characteristics of the item incomplete and even produce noise. Aiming at the above two points, a KGDP recommendation algorithm based on knowledge graph is proposed. Firstly, some items are randomly selected from user interaction records as user related items, and the neighbor entities of the items are selected as item related entities; Then, the selected user related items are fused into user features through deep neural network, which enriches user features and aggregates the related entities of the items separately; Secondly, through two deep neural networks, users can perceive item characteristics and neighbor characteristics respectively, that is, non-linear interaction. Finally, a single-layer perceptron is used to adjust the output weight of interactive features for score prediction. Experiments on two real datasets commonly used in recommendation algorithm, compared with the baseline model, the AUC index improved by 9.2% and 2.4% respectively; ACC index improved by 6.6% and 1.9%; F1 index improved by 7.0% and 1.1% respectively; Precision@N index improved by 28.8% and 6.5% respectively; Recall@N index improved by 4.0% and 23.7% respectively; F1@N index improved by 43.3% and 8.4% respectively.

     

/

返回文章
返回