Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks

04/22/2017 ∙ by Federico Monti, et al. ∙ 0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 4

page 5

page 7

Code Repositories

mgcnn

Multi-Graph Convolutional Neural Networks


view repo

magnesium

Multi Graph Convolutional Neural Networks applied to Matrix Completion.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.