Imperial College London

ProfessorMichaelBronstein

Faculty of EngineeringDepartment of Computing

Chair in Machine Learning and Pattern Recognition
 
 
 
//

Contact

 

m.bronstein Website

 
 
//

Location

 

569Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Monti:2017,
author = {Monti, F and Bronstein, MM and Bresson, X},
pages = {3698--3708},
title = {Geometric matrix completion with recurrent multi-graph neural networks},
year = {2017}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - © 2017 Neural information processing systems foundation. All rights reserved. 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 stationary structures on 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 a novel multi-graph convolutional neural network that can learn meaningful statistical graph-structured patterns from users and items, and a recurrent neural network that applies a learnable diffusion on the score matrix. Our neural network system is computationally attractive as it requires a constant number of parameters independent of the matrix size. We apply our method on several standard datasets, showing that it outperforms state-of-the-art matrix completion techniques.
AU - Monti,F
AU - Bronstein,MM
AU - Bresson,X
EP - 3708
PY - 2017///
SN - 1049-5258
SP - 3698
TI - Geometric matrix completion with recurrent multi-graph neural networks
ER -