Graph Convolutional Matrix Completion via Relation Reconstruction

To alleviate sparsity and improve recommender systems performance, it is necessary to go beyond modeling user-item interactions and take auxiliary information into account. Besides user-item interactions, auxiliary information can be used to build relation graphs. Recently, Graph Convolution Networks (GCNs), which can integrate content information and structural information of nodes, have been demonstrated to be powerful in learning on graph data and applied in recommendation systems. However, existing approaches do not consider multiple types of relations between nodes and high-order structural information. In this paper, we propose a new model called Graph Convolutional Matrix Completion via relation reconstruction (RE-GCMC) to capture structural information and relations between nodes in the graph. We construct user-user, item-item, and user-item relation graphs by evaluating the feature similarity of the nodes. Then, we introduce the Graph Convolutional Networks (GCNs) and self-attention mechanism to be applied in the graphs to refine feature embeddings. We apply the proposed model to four datasets and experimental results demonstrate that our approach outperforms state-of-the-art recommender baselines.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Shirui Pan,et al.  DAGCN: Dual Attention Graph Convolutional Networks , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[3]  Wenhui Yu,et al.  Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters , 2020, ICML.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Duc Minh Nguyen,et al.  Extendable Neural Matrix Completion , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Chunyan Miao,et al.  A Boosting Algorithm for Item Recommendation with Implicit Feedback , 2015, IJCAI.

[7]  Xavier Bresson,et al.  Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks , 2017, NIPS.

[8]  Xin Liu,et al.  Learning User Dependencies for Recommendation , 2017, IJCAI.

[9]  Chunyan Miao,et al.  PD-GAN: Adversarial Learning for Personalized Diversity-Promoting Recommendation , 2019, IJCAI.

[10]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[11]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[12]  Lei Zheng,et al.  Spectral collaborative filtering , 2018, RecSys.

[13]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

[14]  Chunyan Miao,et al.  Learning Personalized Itemset Mapping for Cross-Domain Recommendation , 2020, IJCAI.

[15]  Qiong Wu,et al.  Diversified Interactive Recommendation with Implicit Feedback , 2020, AAAI.

[16]  Samy Bengio,et al.  LLORMA: Local Low-Rank Matrix Approximation , 2016, J. Mach. Learn. Res..

[17]  Qiong Wu,et al.  Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation , 2019, ICCSE.

[18]  Irwin King,et al.  STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems , 2019, IJCAI.

[19]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[20]  Pradeep Ravikumar,et al.  Collaborative Filtering with Graph Information: Consistency and Scalable Methods , 2015, NIPS.