Embedding Disentanglement in Graph Convolutional Networks for Recommendation

Recent years have witnessed the rapid development of recommender systems. To improve recommendation performance, many efforts have been made to study how to equip the conventional methods with auxiliary information such as item relations. Meanwhile, a growing body of work has focused on applying graph convolutional networks to recommendation tasks. Thus, it is promising to use graph convolution to model multi-order relations among users and items for improving recommendation performance. However, the existing graph convolution-based recommendation methods may suffer from structural design problems: for methods with embedding transformations in graph convolutional layers, the MLP makes the updated embedding dimensions coupled, hurting the embedding expressivity. While for methods based on simplified graph convolution, removing the parameter matrices makes the model attach the same weight to embeddings in different layers, which may be over-simplified and limit the model expressivity. In this paper, we propose a novel graph convolution-based recommendation method, namely Channel-Independent Graph Convolutional Network (CIGCN). To learn disentangled embeddings, CIGCN uses diagonal parameter matrices as filters in graph convolution, keeping the updated embedding dimensions independent. In addition, with layer-aggregation strategies, the parameters in the diagonal matrices act as trainable weights that attach different importance to the embeddings in each layer and each dimension, enhancing the model expressivity. Results of extensive experiments on four real-world datasets show that CIGCN significantly outperforms baseline methods in recommendation accuracy and could learn better representations for users and items.