AF-GCN: Attribute-Fusing Graph Convolution Network for Recommendation
Guowei Yue, Rui Xiao, Zhongying Zhao, Chao Li
Abstract
Graph Convolution Networks (GCNs) are playing important role and widely used in recommendation systems. This is benefited from their capability of capturing the collaborative signals of higher-order neighbors by exploiting the graph structure. GCN-based methods have made great success in improving recommending performance, but still suffer from the severe problem of data sparsity. An effective solution to alleviate the data sparsity is to introduce attribute information. However, existing GCN-based methods hardly capture the complex attribute information of users and items and the complicated relationships between users, items, and attributes simultaneously. To address the above problems, we propose a novel attribute-fusing graph convolution network model called AF-GCN. Specifically, we first propose an attention-based attribute fusion strategy by taking account of different effects of attributes. Then, we construct a complex graph containing four kinds of nodes. Finally, we design a particular Laplacian matrix, which leverages the attribute information through graph structure to learn user and item representations better. Extensive experimental results on three real-world datasets demonstrate that the proposed AF-GCN significantly outperforms state-of-the-art methods. The source codes of this work are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/xiaorui-mnaire/af-gcn</uri> .