A novel recommender algorithm based on graph embedding and diffusion sampling

Abstract

SummaryWith the rapid increase in e‐commerce data, recommender systems (RSs) have become the most prevalent methods for providing recommended services in various commercial platforms. Deep learning–based recommender methods improve recommendation results by learning latent representations; however, most cannot capture the correlations between items and ignore additional information such as time information, which leads to suboptimal suggestions. To improve recommendation accuracy, we propose a novel recommender algorithm based on graph embedding and diffusion sampling (graph2vec). Our improved model constructs a graph based on users' behavior histories and embeds the graph to a low‐dimensional vector space with a deep learning approach. To obtain more accurate embedding results, we use a revised sampling method based on information diffusion theory to capture both the depth and breadth information of a graph. Then, we recommend the top‐N items to the target user depending on the final representation vectors. Experiments are carried out with real‐world datasets to demonstrate the superior performance of graph2vec. The results show that browse‐based graph construction and diffuse‐based graph embedding help improve the recommender accuracy of the new model compared with that of the selected state‐of‐the‐art models.

A social hybrid recommendation system using LSTM and CNN

“…Chen et al proposed a graph embedding and diffusion sampling approach for the recommendation system 47 . Based on user behavior history, a graph will be formed and used to provide embedding.…”

“…Chen et al proposed a graph embedding and diffusion sampling approach for the recommendation system. 47 Based on user behavior history, a graph will be formed and used to provide embedding. A sampling method based on information diffusion theory has been used to have accurate embeddings.…”

Special Issue on Computational Intelligence Techniques for Industrial and Medical Applications

“…To improve the recommendation accuracy, the authors in the contribution by Chen et al "A novel recommender algorithm based on graph embedding and diffusion sampling" propose a novel recommender algorithm based on graph embedding and diffusion sampling (graph2vec). 2 Their improved model constructs a graph based on users' behavior histories and embeds the graph to a low-dimensional vector space with a deep learning approach. To obtain a more accurate embedding result, the authors used a revised sampling method based on information diffusion theory to capture both the depth and breadth information of a graph.…”