Community aware graph embedding learning for item recommendation

Due to the heterogeneity of a large amount of real-world data, meta-paths are widely used in recommendation. Such recommendation methods can represent composite relationships between entities, but cannot explore reliable relations between nodes and influence among meta-paths. For solving this problem, a Community Aware Graph Embedding Learning method for Item Recommendation(CAEIRec) is proposed. By adaptively constructing communities for nodes in the graph of entities, the correlations of nodes are embedded in graph learning from the aspect of community structure. Semantic information of users and items are jointly learnt in the embedding. Finally, the embeddings of users and items are fed to extend matrix factorization for getting the top recommendations. A series of comprehensive experiments are conducted on two different public datasets. The empirical results show that CAEIRec is an encouraging recommendation method by the comarison with the state-of-the-art methods. Source code of CAEIRec is available at https://github.com/a545187002/CAEIRec-tensorflow.