Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks

Abstract

Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of graphs, and imposing smoothness priors on these graphs. However, such techniques do not fully exploit the local stationarity structures of user/item graphs, and the number of parameters to learn is linear w.r.t. the number of users and items. We propose a novel approach to overcome these limitations by using geometric deep learning on graphs. Our matrix completion architecture combines graph convolutional neural networks and recurrent neural networks to learn meaningful statistical graph-structured patterns and the non-linear diffusion process that generates the known ratings. This neural network system requires a constant number of parameters independent of the matrix size. We apply our method on both synthetic and real datasets, showing that it outperforms state-of-the-art techniques.

Cited by in corpus (22)

• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• A Gentle Introduction to Deep Learning for Graphs
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Graph signal processing for machine learning: A review and new perspectives
• DeepGCNs: Making GCNs Go as Deep as CNNs
• Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• Invariance-Preserving Localized Activation Functions for Graph Neural Networks
• STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• Sparse Sampling for Inverse Problems with Tensors
• Scalable Probabilistic Matrix Factorization with Graph-Based Priors
• Kernel-based Graph Learning from Smooth Signals: A Functional Viewpoint
• MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs
• Graph Sampling for Matrix Completion Using Recurrent Gershgorin Disc Shift
• Structure fusion based on graph convolutional networks for semi-supervised classification
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• SWAG: Item Recommendations using Convolutions on Weighted Graphs
• Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)
• Temporal Graph Signal Decomposition