Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks

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...

Authors

Federico Monti

Michael M. Bronstein

Xavier Bresson

Related Content

Predicting Future User Activities with Constrained Non-Linear Models

Prediction of future user activities from their history, all past activities, is a challenging problem. One reason is that the....

View publication

High-Performance Incremental SVM Learning on Intel Xeon Phi…

Support vector machines (SVMs) are conventionally batch trained. Such implementations can be very inefficient for online streaming applications demanding real-time....

View publication

Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions

The driving force behind deep networks is their ability to compactly represent rich classes of functions. The primary notion for....

View publication

Stream Aggregation through Order Sampling

This is paper introduces a new single-pass reservoir weighted-sampling stream aggregation algorithm, Priority-Based Aggregation (PBA). While order sampling is a....

View publication

Stay Connected


Keep tabs on all the latest news with our monthly newsletter.