Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach

Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach Lei Chen 1,2, Le Wu 1,2,, Richang Hong 1,2, Kun Zhang 3, Meng Wang 1,2 1 Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology 2 School of Computer Science and Information Engineering, HeFei University of Technology 3 School of Computer Science and Technology, University of Science and Technology of China {chenlei.hfut,lewu.ustc, Abstract Graph Convolutional Networks (GCNs) are state-of-the-art graph based representation learning models by iteratively stacking multiple layers of convolution aggregation operations and nonlinear activation operations. Recently, in Collaborative Filtering (CF) based Recommender Systems (RS), by treating the user-item interaction behavior as a bipartite graph, some researchers model higher-layer collaborative signals with GCNs. These GCN based recommender models show superior performance compared to traditional works. However, these models suffer from training difficulty with nonlinear activations for large user-item graphs. Besides, most GCN based models could not model deeper layers due to the over smoothing effect with the graph convolution operation. In this paper, we revisit GCN based CF models from two aspects. First, we empirically show that removing non-linearities would enhance recommendation performance, which is consistent with the theories in simple graph convolutional networks. Second, we propose a residual network structure that is specifically designed for CF with user-item interaction modeling, which alleviates the over smoothing problem in graph convolution aggregation operation with sparse user-item interaction data.