Graph Convolution Machine for Context-aware Recommender System

The latest advance in recommendation shows that better user and item representations can be learned via performing graph convolutions on the user-item interaction graph. However, such finding is mostly restricted to the collaborative filtering (CF) sce- nario, where the user/item attributes and interaction contexts are not available. In this work, we extend the advantages of graph convolutions to context- aware recommender system (CARS), which repre- sents a generic type of models that can handle var- ious side information. We propose Graph Convo- lution Machine (GCM), an end-to-end framework that consists of three components: an encoder, graph convolution (GC) layers, and a decoder. The encoder projects users, items, and contexts into em- bedding vectors, which are passed to the GC layers that refine user and item embeddings with context- aware graph convolutions on user-item graph. The decoder digests the refined embeddings to output the prediction score by considering the interactions among user, item, and context embeddings. We conduct experiments on three real-world datasets from Yelp, validating the effectiveness of GCM and the benefits of performing graph convolutions for CARS.