数据与计算发展前沿2024，Vol.6Issue(5)：102-110,9.DOI:10.11871/jfdc.issn.2096-742X.2024.05.010
基于图划分的分布式推荐系统
A Distributed Recommender System Based on Graph Partition
摘要
Abstract
[Objective]It is of great significance to design a recommender system with high data process-ing efficiency.[Methods]The graph structure is used to simulate the user preference relation-ship in the recommender system.Through the graph partition algorithm processing,the infor-mation value of the data in the recommender system can be further mined,and the obtained sub-graph data with load balancing can be used as the input of the distributed system.Finally,a dis-tributed recommender system is implemented through the fusion of an adaptive aggregation module.[Results]The system can improve the processing efficiency of the recommender algo-rithm for large-scale data.On the premise that the prediction accuracy does not decline,the al-gorithm can improve the efficiency 6.4 times in a cluster training consisting of 16 CPUs com-pared with a single CPU training.[Conclusions]The experimental results show that the system is effective in rec-ommendation efficiency.关键词
推荐系统/图划分/负载均衡/分布式系统Key words
recommender system/graph partition/load balancing/distributed system引用本文复制引用
杨锦光,熊菲,顾峻瑜,席炜亭..基于图划分的分布式推荐系统[J].数据与计算发展前沿,2024,6(5):102-110,9.基金项目
国家自然科学基金(61872033) （61872033）
国家自然科学基金(72004009) （72004009）
国家重点研发计划(2018YFC0832304) （2018YFC0832304）
北京市科技新星计划(Z201100006820015) （Z201100006820015）
