Graph Convolutional Matrix Completion

TLDR

Matrix completion for recommender systems is framed as link prediction on bipartite user‑item graphs where observed ratings are labeled edges. The authors propose a graph auto‑encoder that uses differentiable message passing on the bipartite interaction graph. It achieves this by applying a graph auto‑encoder that performs differentiable message passing over the bipartite graph. The model achieves competitive performance on standard collaborative filtering benchmarks and outperforms recent state‑of‑the‑art methods when additional feature or social network data are incorporated.

Abstract

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.