Graph Convolutional Matrix Completion
Rianne van den Berg, Thomas Kipf, Max Welling · arXiv (Cornell University) · 2017
We consider matrix completion for recommender systems from the point of view of link prediction on graphs. Interaction data such as movie ratings can be represented by a bipartite user-item graph with labeled edges denoting observed ratings. Building on recent progress in deep learning on graph-structured data, we propose a graph auto-encoder framework based on differentiable message passing on the bipartite interaction graph. Our model shows competitive performance on standard collaborative filtering benchmarks. In settings where complimentary feature information or structured data such as a social network is available, our framework outperforms recent state-of-the-art methods.
Cited by 1,023 works. doi:10.48550/arxiv.1706.02263 Open-access PDF
Authors
References
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- Matrix Factorization Techniques for Recommender Systems
- Restricted Boltzmann machines for collaborative filtering
- Semi-Supervised Classification with Graph Convolutional Networks
- Exact Matrix Completion via Convex Optimization
- Inductive Representation Learning on Large Graphs
- Spectral Networks and Locally Connected Networks on Graphs
- Neural Message Passing for Quantum Chemistry
- AutoRec