Dynamic evolution of multi-graph based collaborative filtering for recommendation systems

The recommendation system is an important and widely used technology in the era of Big Data. Current methods have fused side information into it to alleviate the sparsity problem, one of the key problems of recommendation systems. However, not all the side information can be obtained with high quality, and the specific methods based on side information are not universal. In addition, side information has not been mined by the existing graph-based methods. To address these problems, we propose a Dynamic evolution of Multi-Graph Collaborative Filtering (DMGCF) model to mine and reuse side information. Specifically, we first construct user graph and item graph based on user-item bipartite graph and embeddings to exploit inter-user and inter-item relationships. The two new graphs simulate side information in latent space. Next, we perform a dual-path graph convolution network (GCN) on these three graphs for collaborative filtering. Then, a novel dynamic evolution mechanism is proposed to update and promote the embeddings and graphs collaboratively during the learning process, which produces better embeddings, user and item relationships, as well as the rating scores. We conduct a series of experiments on real-world datasets, and experimental results show the effectiveness of our approach. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

The recommendation system is an important technology in the era of Big Data. Current methods have integrated side information to alleviate the sparsity problem, but not all side information can be obtained with high quality. By proposing the DMGCF model and dynamically evolving multi-graph collaborative filtering, the approach successfully mines and reuses side information, as demonstrated by experimental results.