TY - JOUR A2 - Nazir, Shah AU - Tang, Bing AU - Kang, Linyao AU - Zhang, Li AU - Guo, Feiyan AU - He, Haiwu PY - 2021 DA - 2021/01/05 TI - Collaborative Filtering Recommendation Using Nonnegative Matrix Factorization in GPU-Accelerated Spark Platform SP - 8841133 VL - 2021 AB - Nonnegative matrix factorization (NMF) has been introduced as an efficient way to reduce the complexity of data compression and its capability of extracting highly interpretable parts from data sets, and it has also been applied to various fields, such as recommendations, image analysis, and text clustering.然而,随着矩阵规模的增加,非负矩阵分解处理速度非常慢论文建议并行算法基于spark平台NMF,充分利用模拟计算模式和GPU加速法的长处Spark平台上新GPU加速NM使用Google计算引擎四节多组评价,配置NVIDIAK80CUDA设备,实验结果显示计算时间比方各种矩阵指令的现有解决方案有竞争力此外,还提议加速NMF并行滤波算法,利用数据维度下降和国家MF特征提取的长处以及CUDA多极并行计算模式实验结果显示Spark平台上基于NMF协同滤波有效优于基于用户和基于项目的传统CF高处理速度和高推荐精度SN-1058-9244UR-https://doi.org/101155/2021/841133DO-10.1155/202181133JF-科学编程PB-HindawiKW-ER