Example Recommender System Using Deep Graph Library with a Graph Convolutional Matrix Completion Network
This example is a recommender system for movie reviews. It uses a graph convolutional matrix completion (GCMC) network trained on the MovieLens datasets. These datasets consist of movie titles, genres, and ratings by users.
It uses Apache MXNet as its backend. MXNet built with large tensor support is required. This example shows you how you can build your own container with the necessary dependencies to run the network on Amazon SageMaker.
For more information about Deep Graph Library (DGL) please visit the DGL documentation website: https://docs.dgl.ai