In order to improve the performance of recommender systems, user social information and item attribute information should be integrated when building the prediction model, which is a hotspot and difficulty in the field of recommender systems. In this paper, we propose an extended matrix factorization model based on network representation learning. To characterize users and items comprehensively, we construct the user relation network and the item relation network from the multi-source data. Then the representation vectors of users and items are learned from two networks respectively. The representation vectors learned from the relation networks can characterize users and items more effectively. Since users and items belong to different vector spaces, a matrix is used to connect user and item representation vectors when predicting ratings. To obtain the connection matrix, stochastic gradient descent is applied to minimize the errors between the predicted and observed ratings. Experimental results on two real-world datasets, Yelp and Douban, demonstrate the effectiveness of our model compared to the state-of-the-art recommendation algorithms.

为了提高推荐系统的性能，在构建预测模型时需要结合用户社会信息和物品属性信息，这是推荐系统领域的一个热点和难点。在本文中，我们提出了一种基于网络表示学习的扩展矩阵分解模型。为了全面表征用户和项目，我们从多源数据构建用户关系网络和项目关系网络。然后分别从两个网络中学习用户和项目的表示向量。从关系网络中学习到的表示向量可以更有效地表征用户和项目。由于用户和项目属于不同的向量空间，因此在预测评分时使用矩阵来连接用户和项目表示向量。为了获得连接矩阵，应用随机梯度下降来最小化预测评分和观察评分之间的误差。Yelp 和豆瓣这两个真实世界数据集的实验结果证明了我们的模型与最先进的推荐算法相比的有效性。