Geometric matrix completion with recurrent multi-graph neural networks

Federico Monti, Michael M. Bronstein, Xavier Bresson

Research output: Contribution to journalConference articlepeer-review

347 Scopus citations


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.

Original languageEnglish
Pages (from-to)3698-3708
Number of pages11
JournalAdvances in Neural Information Processing Systems
StatePublished - 2017
Externally publishedYes
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: 4 Dec 20179 Dec 2017


FundersFunder number
ERC Starting307047, 724228
German Excellence Initiative
TU Munich Institute for Advanced Study
Radcliffe Institute for Advanced Study, Harvard University
Seventh Framework Programme291763, NRFF2017-10


    Dive into the research topics of 'Geometric matrix completion with recurrent multi-graph neural networks'. Together they form a unique fingerprint.

    Cite this