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 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 language | English |
---|---|
Pages (from-to) | 3698-3708 |
Number of pages | 11 |
Journal | Advances in Neural Information Processing Systems |
Volume | 2017-December |
State | Published - 2017 |
Externally published | Yes |
Event | 31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States Duration: 4 Dec 2017 → 9 Dec 2017 |
Funding
Funders | Funder number |
---|---|
ERC Starting | 307047, 724228 |
German Excellence Initiative | |
TU Munich Institute for Advanced Study | |
Radcliffe Institute for Advanced Study, Harvard University | |
Seventh Framework Programme | 291763, NRFF2017-10 |