社交网络下基于列表级排序学习的推荐算法  

List-wise learning to rank for recommendation on social networks

作　　者：郭绍翠[1,2] 童向荣 杨旭 GUO Shao-cui;TONG Xiang-rong;YANG Xu(Open Education College,Yantai Vocational College,Yantai 264005,China;School of Computer and Control Engineering,Yantai University,Yantai 264005,China;Department of Computer Science and Technology,Tongji University,Shanghai 201804,China)

机构地区：[1]烟台职业学院开放教育学院,山东烟台264005 [2]烟台大学计算机与控制工程学院,山东烟台264005 [3]同济大学计算机科学与技术系,上海201804

出　　处：《计算机工程与设计》2019年第6期1763-1768,1795,共7页Computer Engineering and Design

基　　金：国家自然科学基金项目(61572418)

摘　　要：将列表级排序学习和推荐算法相结合,能够有效提高传统推荐系统返回结果的准确性。针对社交网络环境,提出一种基于列表级排序学习的推荐算法L2 R2SN (list-wise learning to rank for recommendation for social networks)。从社交网络中挖掘出用户好友潜在的影响特征,以及物品潜在的隐性特征,融入列表级排序学习的推荐模型中,通过梯度下降方法迭代训练模型参数获得模型的最优解,将物品列表中排序较前的top-k个物品推送给用户。多组实验结果表明,L2 R2SN算法能够有效提高推荐结果的准确性,更为有效地反映用户的偏好。Combining list-wise learning to rank and recommendation algorithms can improve the accuracy of results of traditional recommendation systems. Based on list-wise learning to rank, an efficient recommendation algorithm L2 R2 SN (list-wise learning to rank for recommendation for social networks) on social network environments was proposed. The potential impact features of user ’s friends from social networks and the potential hidden features of items were extracted, and these features were integrated into the list-wise learning to rank based recommendation models. The strategy of gradient descent iterative training was used to obtain the optimal solution of the models. The top- k items were recommended to the users. Experimental results show that the L 2 R 2 SN algorithm can improve the accuracy of the recommendation results effectively and reflect the user’s preference more effectively.

关 键 词：社交网络 排序学习 推荐系统 梯度下降 机器学习 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]