Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks

by   Federico Monti, et al.

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.


page 3

page 4

page 5

page 7


Convolutional Geometric Matrix Completion

Geometric matrix completion (GMC) has been proposed for recommendation b...

Geometric Matrix Completion via Sylvester Multi-Graph Neural Network

Despite the success of the Sylvester equation empowered methods on vario...

Collaborative Self-Attention for Recommender Systems

Recommender systems (RS), which have been an essential part in a wide ra...

MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs

We consider a discrete-valued matrix completion problem for recommender ...

Geometric Matrix Completion with Deep Conditional Random Fields

The problem of completing high-dimensional matrices from a limited set o...

Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networks

Matrix completion problems arise in many applications including recommen...

Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution

Inductive one-bit matrix completion is motivated by modern applications ...

Code Repositories


Multi-Graph Convolutional Neural Networks

view repo


Multi Graph Convolutional Neural Networks applied to Matrix Completion.

view repo

Please sign up or login with your details

Forgot password? Click here to reset