Collaborative Filtering Model of Graph Neural Network Based on Random Walk

This paper proposes a novel graph neural network recommendation method to alleviate the user cold-start problem caused by too few relevant items in personalized collaborative filtering. A deep feedforward is constructed transform bipartite of user–item interactions into spectral domain, using random wandering discover potential correlation information between users and items. Then, finite-order polynomial used optimize convolution process accelerate convergence convolutional network, so that connections domain can be discovered quickly. We conducted experiments on classic dataset MovieLens-1M. The recall precision were improved, results show improve accuracy results, tap association more effectively, significantly problem.