Inductive Matrix Completion Based on Graph Neural Networks

Abstract

We propose an inductive matrix completion model without using side information. By factorizing the (rating) matrix into the product of low-dimensional latent embeddings of rows (users) and columns (items), a majority of existing matrix completion methods are transductive, since the learned embeddings cannot generalize to unseen rows/columns or to new matrices. To make matrix completion inductive, most previous works use content (side information), such as user's age or movie's genre, to make predictions. However, high-quality content is not always available, and can be hard to extract. Under the extreme setting where not any side information is available other than the matrix to complete, can we still learn an inductive matrix completion model? In this paper, we propose an Inductive Graph-based Matrix Completion (IGMC) model to address this problem. IGMC trains a graph neural network (GNN) based purely on 1-hop subgraphs around (user, item) pairs generated from the rating matrix and maps these subgraphs to their corresponding ratings. It achieves highly competitive performance with state-of-the-art transductive baselines. In addition, IGMC is inductive -- it can generalize to users/items unseen during the training (given that their interactions exist), and can even transfer to new tasks. Our transfer learning experiments show that a model trained out of the MovieLens dataset can be directly used to predict Douban movie ratings with surprisingly good performance. Our work demonstrates that: 1) it is possible to train inductive matrix completion models without using side information while achieving similar or better performances than state-of-the-art transductive methods; 2) local graph patterns around a (user, item) pair are effective predictors of the rating this user gives to the item; and 3) Long-range dependencies might not be necessary for modeling recommender systems.

arXiv commentAccepted as a spotlight presentation at ICLR-2020

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Link Prediction in Complex Networks: A Survey
• Spectral Networks and Locally Connected Networks on Graphs
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Fast Graph Representation Learning with PyTorch Geometric
• Graph Convolutional Matrix Completion
• How to project a bipartite network?
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Gated Graph Sequence Neural Networks
• How Powerful are Graph Neural Networks?
• A Neural Autoregressive Approach to Collaborative Filtering
• Matrix Completion on Graphs
• Neural Network Matrix Factorization
• Provable Inductive Matrix Completion
• Deep Models of Interactions Across Sets

Cited by in corpus (7)

• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• AGL: a Scalable System for Industrial-purpose Graph Machine Learning
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Graph Classification by Mixture of Diverse Experts
• Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction
• Inductive Matrix Completion Using Graph Autoencoder
• Hierarchical BiGraph Neural Network as Recommendation Systems