摘要
针对数据稀疏且存在不均衡标签的问题,提出一种基于半监督学习模型的协同过滤推荐算法.半监督学习可以同时利用有标签和无标签数据,根据有标签数据的监督信息来给无标签数据打上伪标签,通过对无标签数据的预测,有效缓解数据的稀疏性,从而提升模型推荐效果.通过对比实验表明,在不同的公开数据集中,本文算法的均方根误差与平均绝对误差均比传统推荐方法有所降低,验证了其有效性.
Aiming at the problem of sparse data and imbalanced labels, a collaborative filtering recommendation algorithm based on semi-supervised learning model is proposed.Semi-supervised learning can use labeled and unlabeled data at the same time, and pseudo-label unlabeled data based on the supervision information of labeled data.Through the prediction of unlabeled data, the sparsity of the data can be effectively alleviated and the model recommendation effect can be improved.Comparative experiments show that in different public data sets, the root mean square error and average absolute error of the algorithm in this paper are both lower than the traditional recommendation method, which effectively verifies its effectiveness.
作者
崔莹莹
陈卓
王红霞
CUI Ying-ying;CHEN Zhuo;WANG Hong-xia(College of Information Science and Technology,Qingdao University of Science&Technology,Qingdao 266061,China)
出处
《东北师大学报（自然科学版）》
CAS
北大核心
2022年第3期60-66,共7页
Journal of Northeast Normal University(Natural Science Edition)
基金
国家自然科学基金资助项目(6217072142)
山东省自然科学基金资助项目(ZR2021MF092)。
关键词
矩阵分解
推荐算法
半监督学习
深度学习
matrix decomposition
recommendation algorithm
semi-supervised learning
deep learning
